Ship the Narratio credential forwarding update

0f841fd Forward Scriptorium credentials in the D&D suite

git-subtree-dir: roles/pipeline
git-subtree-split: 0f841fd91ffc533aeec0ec688e81c24bd187a845

README.md

@@ -8,6 +8,17 @@ Release `0.1.0` contains the reviewed `rakestraw.dnd_pipeline` `v0.1.0`
 snapshot and pins the Seriatim, Audita, Notarius, Scriptorium, and Narratio
 roles to their respective `v0.1.0` releases.
 
+The current development snapshot integrates Narratio v3.1.0, Notarius v0.8.1,
+Audita v2.0.1, and Scriptorium v0.15.0 through public standalone role pins.
+It includes the suite's Audita backend/profile configuration and Narratio and
+Notarius testing overlays. Narratio now selects the existing OpenRouter
+credential name for Scriptorium as well as Notarius; see the pipeline role's
+credential guidance for provisioning and retries. This does not replace or
+modify the published `0.1.0` release artifact. Review the [pipeline role
+migration notes](roles/pipeline/README.md)
+before upgrading inventory or application-owned manifests; this collection
+does not convert existing manifests. Seriatim remains v1.5.0.
+
 ## Install release 0.1.0
 
 Download the tagged compatibility manifest and install its exact standalone

requirements.yml

@@ -7,19 +7,19 @@ roles:
   - name: rakestraw.audita
     src: https://gitea.maximumdirect.net/eric/ansible-role-audita.git
     scm: git
-    version: v0.1.0
+    version: c3dd59f5ac9b942306ffe540ae9e71d493998137
   - name: rakestraw.notarius
     src: https://gitea.maximumdirect.net/eric/ansible-role-notarius.git
     scm: git
-    version: v0.1.0
+    version: 6aef48b7e12e3651971444b8c224d96ff1879e6c
   - name: rakestraw.scriptorium
     src: https://gitea.maximumdirect.net/eric/ansible-role-scriptorium.git
     scm: git
-    version: v0.1.0
+    version: b174c8c2990bb79f8149d8f288c5e06ccb42bd73
   - name: rakestraw.narratio
     src: https://gitea.maximumdirect.net/eric/ansible-role-narratio.git
     scm: git
-    version: v0.1.0
+    version: 758aed7a74c9a64ad02e13ff551b4f7aea16b3af
 collections:
   - name: ansible.posix
     version: 2.2.0

roles/pipeline/README.md

@@ -18,7 +18,8 @@ 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` release of each role. This standalone role is named
+`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
@@ -60,11 +61,11 @@ The compatible application versions are selected through these variables:
 
 | Variable | Default |
 | --- | --- |
-| `dnd_pipeline_audita_version` | `v0.9.1` |
+| `dnd_pipeline_audita_version` | `v2.0.1` |
-| `dnd_pipeline_narratio_version` | `v2.1.1` |
+| `dnd_pipeline_narratio_version` | `v3.1.0` |
-| `dnd_pipeline_notarius_version` | `v0.7.0` |
+| `dnd_pipeline_notarius_version` | `v0.8.1` |
 | `dnd_pipeline_seriatim_version` | `v1.5.0` |
-| `dnd_pipeline_scriptorium_version` | `v0.13.0` |
+| `dnd_pipeline_scriptorium_version` | `v0.15.0` |
 | `dnd_pipeline_manage_build_dependencies` | `true` |
 | `dnd_pipeline_go_snap_channel` | `1.26/stable` |
 | `dnd_pipeline_go_binary` | `/snap/bin/go` |
@@ -118,20 +119,64 @@ chosen policy value when their deployment requires it.
 | --- | --- |
 | `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_backends` | Native `dnd` backend at `https://inference.ai.rakestrawhome.com/v1`, credential `AUDITA_LLM_API_KEY`, shared concurrency `4` |
-| `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_profiles` | Complete native `dnd-proposal` and `dnd-validation` mappings using `google/gemma-4-31b-it` and 900-second attempt timeouts |
-| `dnd_pipeline_audita_concurrency_*` | total, proposal, and validation concurrency of `4` |
+| `dnd_pipeline_audita_llm_proposal_profile` | `dnd-proposal` |
+| `dnd_pipeline_audita_llm_validation_profile` | `dnd-validation` |
+| `dnd_pipeline_audita_llm_transient_retries`, `dnd_pipeline_audita_llm_repair_attempts`, `dnd_pipeline_audita_llm_operation_timeout` | `null`; omit overrides and use native defaults |
 | `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_normalization_*` | `3.0` maximum and ellipsis gaps, `240.0` 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 |
+| `dnd_pipeline_audita_diagnostics_work_dir` | `/tmp/audita` |
 
-Audita's proposal and validation settings independently remain overrideable,
+Audita owns its backend and LLM policy. The suite writes each complete profile
-but both default to the one typed `AUDITA_LLM_API_KEY` reference Narratio can
+mapping to `/usr/local/etc/audita/profiles/<key>.yml`; keys must be filename-safe
-forward. Audita owns its endpoint, model, tuning, and diagnostics configuration;
+IDs matching each mapping's `id`. Inventory may replace the mappings and selected
-Narratio receives its managed Audita configuration path and supplies the
+IDs. Narratio forwards the configured credential names, while Audita's native
-run-specific output path.
+configuration resolves them. The role does not remove old profile files.
+
+For inventories upgrading from the prior suite, replace the separate Audita
+proposal/validation endpoint, model, key, timeout, and concurrency variables
+with `dnd_pipeline_audita_backends` and `dnd_pipeline_audita_profiles`, then
+select profile IDs with the two `dnd_pipeline_audita_llm_*_profile` variables.
+Replace `dnd_pipeline_narratio_notarius_llm_api_key` with
+`dnd_pipeline_narratio_notarius_credentials`, and use
+`dnd_pipeline_narratio_audita_credentials` for Audita's backend credential
+names. The old diagnostics retention variable is no longer forwarded.
+
+The old per-purpose Audita endpoint and API-key names now belong to the
+backend map; both default profiles share the `dnd` backend and its one
+concurrency limit. Old proposal and validation models and per-attempt timeouts
+belong in complete profile mappings. The default 900-second value is retained
+per attempt; `dnd_pipeline_audita_llm_operation_timeout` is an independent
+whole-operation deadline and defaults to `null`, leaving Audita's native
+policy in charge. The former `*_max_retries` variables do not have a direct
+one-to-one replacement: use the optional Audita transient retry and repair
+attempt settings according to the desired native behavior. Optional retry
+pass-throughs for Notarius PromptKit and Scriptorium likewise default to
+`null`; an explicit `0` is forwarded, not treated as omission.
+
+Include each backend credential name in
+`dnd_pipeline_narratio_audita_credentials` and make its value available to
+Narratio through its process environment or supported secret files.
+`dnd_pipeline_secrets` is the suite's optional file-provisioning interface,
+not a requirement to store credentials on disk. Narratio forwards only names in
+that list and does not discover them from Audita's configuration. The
+Notarius list is independent. For profile overrides, use filename-safe map
+keys equal to each profile's native `id`; the suite writes each map value
+unchanged and does not merge individual fields. See [Audita's v2 configuration
+migration](https://gitea.maximumdirect.net/eric/audita/src/tag/v2.0.1/docs/migrations/v2.md)
+for backend and profile migration; this role does not convert caller-owned
+configuration.
+
+Existing Narratio session manifests need a separate migration before opening
+affected sessions with v3. Stop activity for the session and back up its local
+manifest. Follow [Narratio's manifest overlay-provenance migration](https://gitea.maximumdirect.net/eric/narratio/src/tag/v3.0.0/docs/operations.md#migrating-manifest-overlay-provenance)
+to rename `effective_config.selected_profile` to `selected_overlay`, or remove
+the retired informational member as upstream permits. Preserve stage records,
+checkpoints, and other progress; do not edit immutable remote snapshots or
+force all stages to rerun. The role performs no session migration.
 
 | Variable | Default |
 | --- | --- |
@@ -146,12 +191,31 @@ run-specific output path.
 | `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_notarius_promptkit_transient_retries` | `null`; native default |
+| `dnd_pipeline_scriptorium_transient_retries` | `null`; native default |
+| `dnd_pipeline_narratio_audita_credentials` | `[AUDITA_LLM_API_KEY]` |
+| `dnd_pipeline_narratio_notarius_credentials` | `[OPENROUTER_API_KEY]` |
+| `dnd_pipeline_narratio_scriptorium_credentials` | `[OPENROUTER_API_KEY]` |
 
 `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.
 
+Narratio v3.1.0 forwards the selected Scriptorium credential names for trim,
+analysis, character families, and render-debug calls. The Scriptorium and
+Notarius lists independently default to the existing `OPENROUTER_API_KEY` name;
+using the same provisioned value does not couple their selections. Inventory
+may replace the Scriptorium list, set `[]` to forward nothing, or set `null` to
+omit the field. Each selected name must resolve to a nonempty value when
+Narratio loads configuration, even for inspection commands. Values may come
+from Narratio's process environment or its existing secrets directory;
+`dnd_pipeline_secrets` is optional file provisioning, not the only source.
+After upgrading and provisioning the selected key, retry a failed trim or
+analysis normally. Do not force already successful work solely because a
+credential was added or rotated.
+
 ### Storage and publication policy
 
 The suite selects Narratio's S3 backend and the established Backblaze-compatible
@@ -219,24 +283,44 @@ suite-owned base fragments in this fixed order:
 ├── artifacts/deranged-rumors.yml
 ├── artifacts/scene-map.yml
 ├── artifact-families/character-meta-analysis.yml
-└── profiles/testing.yml
+└── overlays/testing.yml
 ```
 
-The `testing` profile is an overlay, not a second configuration tree. It only
+Notarius follows the corresponding base-and-overlay layout:
-sets the Scriptorium `profile_id` for the four artifact sources and the one
+
-family. Its default, `gemini-flash-latest`, is an inexpensive development
+```text
+/usr/local/etc/notarius/
+├── config.yml
+├── pipelines/dnd-session.yml
+└── overlays/testing.yml
+```
+
+The `testing` overlay is 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
 ```
 
+Narratio selects it with `--overlay testing`, and direct Notarius commands
+use `--config-overlay testing`; the former `--profile` and
+`--config-profile` selectors are retired. Previously deployed
+`profiles/testing.yml` files are ignored, not pruned. Renaming the selected
+overlay normally changes configuration identity, so cached work tied to the
+old named selection may not be reused.
+
 ### 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/overlays/testing.yml` overlay changes only
+the selected suite pipeline's LLM profile.
 
 | Variable | Default policy |
 | --- | --- |
@@ -244,15 +328,20 @@ The Notarius root configuration imports the fixed
 | `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_credentials` | `[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.
+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
@@ -270,10 +359,13 @@ 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. Base and `testing` configurations select the
+created by Notarius during use. See the [Notarius v0.8.1 release notes](https://gitea.maximumdirect.net/eric/notarius/src/tag/v0.8.1/docs/releases/v0.8.1.md)
-same `dnd-extraction` profile and Notarius pipeline; the testing overlay changes
+for its PromptKit dependency and profile-source identity changes.
-only Scriptorium profiles, so a real testing run may invoke Notarius. The
+Existing checkpoints with the previous profile-source identity are not reused;
-integration suite performs offline configuration inspection only.
+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
 
@@ -285,7 +377,7 @@ the party-driven character family:
 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
+  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --overlay testing
 sudo -u narratio narratio config artifacts \
   --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs
 sudo -u narratio narratio config diff default testing \

roles/pipeline/defaults/main.yml

@@ -1,9 +1,9 @@
 ---
-dnd_pipeline_audita_version: v0.9.1
+dnd_pipeline_audita_version: v2.0.1
-dnd_pipeline_narratio_version: v2.1.1
+dnd_pipeline_narratio_version: v3.1.0
-dnd_pipeline_notarius_version: v0.7.0
+dnd_pipeline_notarius_version: v0.8.1
 dnd_pipeline_seriatim_version: v1.5.0
-dnd_pipeline_scriptorium_version: v0.13.0
+dnd_pipeline_scriptorium_version: v0.15.0
 dnd_pipeline_manage_build_dependencies: true
 dnd_pipeline_go_snap_channel: 1.26/stable
 dnd_pipeline_go_binary: /snap/bin/go
@@ -26,25 +26,33 @@ dnd_pipeline_audita_pipeline_modules:
   - spoken_word
   - grammar
 dnd_pipeline_audita_output_schema: audita-v1
-dnd_pipeline_audita_llm_proposal_base_url: https://inference.ai.rakestrawhome.com/v1
+dnd_pipeline_audita_backends:
-dnd_pipeline_audita_llm_proposal_model: google/gemma-4-31b-it
+  dnd:
-dnd_pipeline_audita_llm_proposal_api_key_env: AUDITA_LLM_API_KEY
+    endpoint: https://inference.ai.rakestrawhome.com/v1
-dnd_pipeline_audita_llm_proposal_timeout: 900s
+    credential: AUDITA_LLM_API_KEY
-dnd_pipeline_audita_llm_proposal_max_retries: 3
+    concurrency: 4
-dnd_pipeline_audita_llm_validation_base_url: https://inference.ai.rakestrawhome.com/v1
+dnd_pipeline_audita_profiles:
-dnd_pipeline_audita_llm_validation_model: google/gemma-4-31b-it
+  dnd-proposal:
-dnd_pipeline_audita_llm_validation_api_key_env: AUDITA_LLM_API_KEY
+    id: dnd-proposal
-dnd_pipeline_audita_llm_validation_timeout: 900s
+    backend: dnd
-dnd_pipeline_audita_llm_validation_max_retries: 3
+    model: google/gemma-4-31b-it
-dnd_pipeline_audita_concurrency_total_llm: 4
+    timeout_seconds: 900
-dnd_pipeline_audita_concurrency_proposal_llm: 4
+  dnd-validation:
-dnd_pipeline_audita_concurrency_validation_llm: 4
+    id: dnd-validation
+    backend: dnd
+    model: google/gemma-4-31b-it
+    timeout_seconds: 900
+dnd_pipeline_audita_llm_proposal_profile: dnd-proposal
+dnd_pipeline_audita_llm_validation_profile: dnd-validation
+dnd_pipeline_audita_llm_transient_retries: null
+dnd_pipeline_audita_llm_repair_attempts: null
+dnd_pipeline_audita_llm_operation_timeout: null
 dnd_pipeline_audita_chunking_target_sections: 8
 dnd_pipeline_audita_chunking_max_section_tokens: 6144
 dnd_pipeline_audita_chunking_min_section_tokens: 2048
-dnd_pipeline_audita_normalization_max_segment_gap: 3s
+dnd_pipeline_audita_normalization_max_segment_gap: 3.0
-dnd_pipeline_audita_normalization_ellipsis_gap: 3s
+dnd_pipeline_audita_normalization_ellipsis_gap: 3.0
-dnd_pipeline_audita_normalization_max_segment_duration: 240s
+dnd_pipeline_audita_normalization_max_segment_duration: 240.0
 dnd_pipeline_audita_normalization_max_segment_tokens: 2048
 dnd_pipeline_audita_thresholds_glossary: 0.8
 dnd_pipeline_audita_thresholds_homophones: 0.8
@@ -55,10 +63,9 @@ dnd_pipeline_audita_context_description: >-
   It may contain some unrelated pre-session or post-session banter, in addition
   to actual D&D gameplay.
 dnd_pipeline_audita_diagnostics_work_dir: /tmp/audita
-dnd_pipeline_audita_diagnostics_retention: auto
 dnd_pipeline_notarius_pipelines:
   dnd-session:
-    llm_profile: dnd-extraction
+    llm_profile: gpt-terra-latest
     input:
       module: seriatim
     chunk:
@@ -207,6 +214,9 @@ dnd_pipeline_notarius_pipelines:
 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_notarius_promptkit_transient_retries: null
+dnd_pipeline_scriptorium_transient_retries: null
 dnd_pipeline_narratio_workspace_cleanup_after_publish: true
 dnd_pipeline_narratio_storage_backend: s3
 dnd_pipeline_narratio_storage_s3_bucket: rakestraw-assets
@@ -243,7 +253,12 @@ 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_notarius_pipeline_id: dnd-session
-dnd_pipeline_narratio_notarius_llm_api_key: OPENROUTER_API_KEY
+dnd_pipeline_narratio_audita_credentials:
+  - AUDITA_LLM_API_KEY
+dnd_pipeline_narratio_notarius_credentials:
+  - OPENROUTER_API_KEY
+dnd_pipeline_narratio_scriptorium_credentials:
+  - OPENROUTER_API_KEY
 dnd_pipeline_narratio_notarius_resume: true
 dnd_pipeline_narratio_notarius_references:
   party: narratio.input.party

roles/pipeline/meta/argument_specs.yml

@@ -97,58 +97,34 @@ argument_specs:
         type: str
         required: true
         description: Audita output schema shared with Narratio.
-      dnd_pipeline_audita_llm_proposal_base_url:
+      dnd_pipeline_audita_backends:
+        type: dict
+        required: true
+        description: Native Audita backend definitions.
+      dnd_pipeline_audita_profiles:
+        type: dict
+        required: true
+        description: Native Audita profiles keyed by filename-safe IDs matching each mapping's id.
+      dnd_pipeline_audita_llm_proposal_profile:
         type: str
         required: true
-        description: Audita proposal LLM endpoint.
+        description: Audita proposal profile ID.
-      dnd_pipeline_audita_llm_proposal_model:
+      dnd_pipeline_audita_llm_validation_profile:
         type: str
         required: true
-        description: Audita proposal LLM model.
+        description: Audita validation profile ID.
-      dnd_pipeline_audita_llm_proposal_api_key_env:
+      dnd_pipeline_audita_llm_transient_retries:
-        type: str
-        required: true
-        description: Proposal LLM API-key environment variable name.
-      dnd_pipeline_audita_llm_proposal_timeout:
-        type: str
-        required: true
-        description: Proposal LLM timeout.
-      dnd_pipeline_audita_llm_proposal_max_retries:
         type: int
-        required: true
+        required: false
-        description: Proposal LLM retry count.
+        description: Optional Audita transient retry override.
-      dnd_pipeline_audita_llm_validation_base_url:
+      dnd_pipeline_audita_llm_repair_attempts:
-        type: str
-        required: true
-        description: Audita validation LLM endpoint.
-      dnd_pipeline_audita_llm_validation_model:
-        type: str
-        required: true
-        description: Audita validation LLM model.
-      dnd_pipeline_audita_llm_validation_api_key_env:
-        type: str
-        required: true
-        description: Validation LLM API-key environment variable name.
-      dnd_pipeline_audita_llm_validation_timeout:
-        type: str
-        required: true
-        description: Validation LLM timeout.
-      dnd_pipeline_audita_llm_validation_max_retries:
         type: int
-        required: true
+        required: false
-        description: Validation LLM retry count.
+        description: Optional Audita repair attempt override.
-      dnd_pipeline_audita_concurrency_total_llm:
+      dnd_pipeline_audita_llm_operation_timeout:
-        type: int
+        type: str
-        required: true
+        required: false
-        description: Total Audita LLM concurrency.
+        description: Optional Audita whole-operation deadline override.
-      dnd_pipeline_audita_concurrency_proposal_llm:
-        type: int
-        required: true
-        description: Proposal Audita LLM concurrency.
-      dnd_pipeline_audita_concurrency_validation_llm:
-        type: int
-        required: true
-        description: Validation Audita LLM concurrency.
       dnd_pipeline_audita_chunking_target_sections:
         type: int
         required: true
@@ -162,15 +138,15 @@ argument_specs:
         required: true
         description: Audita minimum section tokens.
       dnd_pipeline_audita_normalization_max_segment_gap:
-        type: str
+        type: float
         required: true
         description: Audita maximum segment gap.
       dnd_pipeline_audita_normalization_ellipsis_gap:
-        type: str
+        type: float
         required: true
         description: Audita ellipsis gap.
       dnd_pipeline_audita_normalization_max_segment_duration:
-        type: str
+        type: float
         required: true
         description: Audita maximum segment duration.
       dnd_pipeline_audita_normalization_max_segment_tokens:
@@ -201,10 +177,6 @@ argument_specs:
         type: str
         required: true
         description: Audita diagnostics work directory.
-      dnd_pipeline_audita_diagnostics_retention:
-        type: str
-        required: true
-        description: Audita diagnostics retention policy.
       dnd_pipeline_notarius_pipelines:
         type: dict
         required: true
@@ -221,6 +193,18 @@ argument_specs:
         type: bool
         required: true
         description: Whether Notarius records checkpoints.
+      dnd_pipeline_notarius_testing_llm_profile:
+        type: str
+        required: true
+        description: Notarius LLM profile selected by the testing overlay.
+      dnd_pipeline_notarius_promptkit_transient_retries:
+        type: int
+        required: false
+        description: Optional Notarius PromptKit transient retry override.
+      dnd_pipeline_scriptorium_transient_retries:
+        type: int
+        required: false
+        description: Optional Scriptorium transient retry override.
       dnd_pipeline_narratio_workspace_cleanup_after_publish:
         type: bool
         required: true
@@ -309,10 +293,21 @@ argument_specs:
         type: str
         required: true
         description: Notarius pipeline selected by Narratio.
-      dnd_pipeline_narratio_notarius_llm_api_key:
+      dnd_pipeline_narratio_audita_credentials:
-        type: str
+        type: list
+        elements: str
         required: true
-        description: Environment-variable name forwarded by Narratio to Notarius.
+        description: Credential names forwarded by Narratio to Audita.
+      dnd_pipeline_narratio_notarius_credentials:
+        type: list
+        elements: str
+        required: true
+        description: Credential names forwarded by Narratio to Notarius.
+      dnd_pipeline_narratio_scriptorium_credentials:
+        type: list
+        elements: str
+        required: false
+        description: Optional credential names forwarded by Narratio to Scriptorium.
       dnd_pipeline_narratio_notarius_resume:
         type: bool
         required: true

roles/pipeline/meta/main.yml

@@ -55,18 +55,19 @@ dependencies:
       narratio_seriatim_binary: /usr/local/bin/seriatim
       narratio_audita_binary: /usr/local/bin/audita
       narratio_audita_config_path: /usr/local/etc/audita/config.yml
-      narratio_audita_llm_api_key: "{{ dnd_pipeline_audita_llm_proposal_api_key_env }}"
+      narratio_audita_credentials: "{{ dnd_pipeline_narratio_audita_credentials }}"
       narratio_notarius_binary: /usr/local/bin/notarius
       narratio_notarius_config_path: /usr/local/etc/notarius/config.yml
       narratio_notarius_enabled: true
       narratio_notarius_pipeline_id: "{{ dnd_pipeline_narratio_notarius_pipeline_id }}"
       narratio_notarius_working_directory: /usr/local/etc/notarius
-      narratio_notarius_llm_api_key: "{{ dnd_pipeline_narratio_notarius_llm_api_key }}"
+      narratio_notarius_credentials: "{{ dnd_pipeline_narratio_notarius_credentials }}"
       narratio_notarius_resume: "{{ dnd_pipeline_narratio_notarius_resume }}"
       narratio_notarius_references: "{{ dnd_pipeline_narratio_notarius_references }}"
       narratio_notarius_outputs: "{{ dnd_pipeline_narratio_notarius_outputs }}"
       narratio_scriptorium_binary: /usr/local/bin/scriptorium
       narratio_scriptorium_config_path: /usr/local/etc/scriptorium/config.yml
+      narratio_scriptorium_credentials: "{{ dnd_pipeline_narratio_scriptorium_credentials }}"
   - role: rakestraw.seriatim
     vars:
       seriatim_version: "{{ dnd_pipeline_seriatim_version }}"
@@ -85,19 +86,13 @@ dependencies:
       audita_config_file_mode: "{{ dnd_pipeline_config_file_mode }}"
       audita_pipeline_modules: "{{ dnd_pipeline_audita_pipeline_modules }}"
       audita_output_schema: "{{ dnd_pipeline_audita_output_schema }}"
-      audita_llm_proposal_base_url: "{{ dnd_pipeline_audita_llm_proposal_base_url }}"
+      audita_backends: "{{ dnd_pipeline_audita_backends }}"
-      audita_llm_proposal_model: "{{ dnd_pipeline_audita_llm_proposal_model }}"
+      audita_profiles_dir: /usr/local/etc/audita/profiles
-      audita_llm_proposal_api_key_env: "{{ dnd_pipeline_audita_llm_proposal_api_key_env }}"
+      audita_llm_proposal_profile: "{{ dnd_pipeline_audita_llm_proposal_profile }}"
-      audita_llm_proposal_timeout: "{{ dnd_pipeline_audita_llm_proposal_timeout }}"
+      audita_llm_validation_profile: "{{ dnd_pipeline_audita_llm_validation_profile }}"
-      audita_llm_proposal_max_retries: "{{ dnd_pipeline_audita_llm_proposal_max_retries }}"
+      audita_llm_transient_retries: "{{ dnd_pipeline_audita_llm_transient_retries }}"
-      audita_llm_validation_base_url: "{{ dnd_pipeline_audita_llm_validation_base_url }}"
+      audita_llm_repair_attempts: "{{ dnd_pipeline_audita_llm_repair_attempts }}"
-      audita_llm_validation_model: "{{ dnd_pipeline_audita_llm_validation_model }}"
+      audita_llm_operation_timeout: "{{ dnd_pipeline_audita_llm_operation_timeout }}"
-      audita_llm_validation_api_key_env: "{{ dnd_pipeline_audita_llm_validation_api_key_env }}"
-      audita_llm_validation_timeout: "{{ dnd_pipeline_audita_llm_validation_timeout }}"
-      audita_llm_validation_max_retries: "{{ dnd_pipeline_audita_llm_validation_max_retries }}"
-      audita_concurrency_total_llm: "{{ dnd_pipeline_audita_concurrency_total_llm }}"
-      audita_concurrency_proposal_llm: "{{ dnd_pipeline_audita_concurrency_proposal_llm }}"
-      audita_concurrency_validation_llm: "{{ dnd_pipeline_audita_concurrency_validation_llm }}"
       audita_chunking_target_sections: "{{ dnd_pipeline_audita_chunking_target_sections }}"
       audita_chunking_max_section_tokens: "{{ dnd_pipeline_audita_chunking_max_section_tokens }}"
       audita_chunking_min_section_tokens: "{{ dnd_pipeline_audita_chunking_min_section_tokens }}"
@@ -111,7 +106,6 @@ dependencies:
       audita_thresholds_grammar: "{{ dnd_pipeline_audita_thresholds_grammar }}"
       audita_context_description: "{{ dnd_pipeline_audita_context_description }}"
       audita_diagnostics_work_dir: "{{ dnd_pipeline_audita_diagnostics_work_dir }}"
-      audita_diagnostics_retention: "{{ dnd_pipeline_audita_diagnostics_retention }}"
   - role: rakestraw.notarius
     vars:
       notarius_version: "{{ dnd_pipeline_notarius_version }}"
@@ -128,6 +122,7 @@ dependencies:
       notarius_cache_chunk_plans_directory: "{{ dnd_pipeline_notarius_cache_root ~ '/chunk-plans' }}"
       notarius_cache_checkpoints_enabled: "{{ dnd_pipeline_notarius_cache_checkpoints_enabled }}"
       notarius_cache_checkpoints_directory: "{{ dnd_pipeline_notarius_cache_root ~ '/checkpoints' }}"
+      notarius_promptkit_transient_retries: "{{ dnd_pipeline_notarius_promptkit_transient_retries }}"
   - role: rakestraw.scriptorium
     vars:
       scriptorium_version: "{{ dnd_pipeline_scriptorium_version }}"
@@ -140,3 +135,4 @@ dependencies:
       scriptorium_config_file_mode: "{{ dnd_pipeline_config_file_mode }}"
       scriptorium_prompt_dir: "{{ dnd_pipeline_prompt_library_root ~ '/prompts' }}"
       scriptorium_schema_dir: "{{ dnd_pipeline_prompt_library_root ~ '/schemas' }}"
+      scriptorium_transient_retries: "{{ dnd_pipeline_scriptorium_transient_retries }}"

roles/pipeline/requirements.yml

@@ -7,16 +7,16 @@ roles:
   - name: rakestraw.audita
     src: https://gitea.maximumdirect.net/eric/ansible-role-audita.git
     scm: git
-    version: v0.1.0
+    version: c3dd59f5ac9b942306ffe540ae9e71d493998137
   - name: rakestraw.notarius
     src: https://gitea.maximumdirect.net/eric/ansible-role-notarius.git
     scm: git
-    version: v0.1.0
+    version: 6aef48b7e12e3651971444b8c224d96ff1879e6c
   - name: rakestraw.scriptorium
     src: https://gitea.maximumdirect.net/eric/ansible-role-scriptorium.git
     scm: git
-    version: v0.1.0
+    version: b174c8c2990bb79f8149d8f288c5e06ccb42bd73
   - name: rakestraw.narratio
     src: https://gitea.maximumdirect.net/eric/ansible-role-narratio.git
     scm: git
-    version: v0.1.0
+    version: 758aed7a74c9a64ad02e13ff551b4f7aea16b3af

roles/pipeline/tasks/main.yml

@@ -144,16 +144,38 @@
     - conf.d
     - artifacts
     - artifact-families
-    - profiles
+    - overlays
 
-- name: Create the Notarius pipeline configuration directory
+- name: Create Notarius configuration directories
   become: true
   ansible.builtin.file:
-    path: /usr/local/etc/notarius/pipelines
+    path: "/usr/local/etc/notarius/{{ item }}"
     state: directory
     owner: "{{ dnd_pipeline_runtime_user }}"
     group: "{{ dnd_pipeline_runtime_group }}"
     mode: "{{ dnd_pipeline_config_directory_mode }}"
+  loop:
+    - pipelines
+    - overlays
+
+- name: Create the Audita profile directory
+  become: true
+  ansible.builtin.file:
+    path: /usr/local/etc/audita/profiles
+    state: directory
+    owner: "{{ dnd_pipeline_runtime_user }}"
+    group: "{{ dnd_pipeline_runtime_group }}"
+    mode: "{{ dnd_pipeline_config_directory_mode }}"
+
+- name: Deploy Audita profiles
+  become: true
+  ansible.builtin.template:
+    src: audita-profile.yml.j2
+    dest: "/usr/local/etc/audita/profiles/{{ item.key }}.yml"
+    owner: "{{ dnd_pipeline_runtime_user }}"
+    group: "{{ dnd_pipeline_runtime_group }}"
+    mode: "{{ dnd_pipeline_config_file_mode }}"
+  loop: "{{ dnd_pipeline_audita_profiles | dict2items }}"
 
 - name: Deploy the Notarius D&D pipeline configuration
   become: true
@@ -164,6 +186,15 @@
     group: "{{ dnd_pipeline_runtime_group }}"
     mode: "{{ dnd_pipeline_config_file_mode }}"
 
+- name: Deploy the Notarius testing overlay
+  become: true
+  ansible.builtin.template:
+    src: notarius-testing.yml.j2
+    dest: /usr/local/etc/notarius/overlays/testing.yml
+    owner: "{{ dnd_pipeline_runtime_user }}"
+    group: "{{ dnd_pipeline_runtime_group }}"
+    mode: "{{ dnd_pipeline_config_file_mode }}"
+
 - name: Deploy Narratio D&D configuration fragments
   become: true
   ansible.builtin.template:
@@ -186,4 +217,4 @@
     - src: character-meta-analysis.yml.j2
       dest: artifact-families/character-meta-analysis.yml
     - src: testing.yml.j2
-      dest: profiles/testing.yml
+      dest: overlays/testing.yml

roles/pipeline/templates/audita-profile.yml.j2

@@ -0,0 +1 @@
+{{ item.value | to_nice_yaml }}

roles/pipeline/templates/notarius-testing.yml.j2

@@ -0,0 +1,3 @@
+pipelines:
+  {{ dnd_pipeline_narratio_notarius_pipeline_id | to_json }}:
+    llm_profile: {{ dnd_pipeline_notarius_testing_llm_profile | to_json }}

roles/pipeline/templates/testing.yml.j2

@@ -1,3 +1,5 @@
+notarius:
+    config_overlay: testing
 scriptorium:
   artifacts:
     session_recap:

roles/pipeline/tests/integration

@@ -44,6 +44,9 @@ baseline_args=(
   -e 'dnd_pipeline_narratio_storage_s3_secret_access_key=OBJECT_STORAGE_KEY'
   -e '{"dnd_pipeline_narratio_workspace_cleanup_after_publish":false,"dnd_pipeline_narratio_storage_s3_force_path_style":false,"dnd_pipeline_narratio_cache_s3_audio":false,"dnd_pipeline_narratio_publish_enabled":true,"dnd_pipeline_narratio_publish_upload_run":true}'
   -e '{"dnd_pipeline_narratio_publish_outputs":[{"source":"narratio.transcript.final","required":true},{"source":"narratio.artifact.session_recap","required":true}]}'
+  -e 'dnd_pipeline_narratio_testing_scriptorium_profile=endpoint-profile'
+  -e 'dnd_pipeline_notarius_testing_llm_profile=gpt-terra-latest'
+  -e '{"dnd_pipeline_audita_llm_transient_retries":null,"dnd_pipeline_audita_llm_repair_attempts":null,"dnd_pipeline_audita_llm_operation_timeout":null,"dnd_pipeline_notarius_promptkit_transient_retries":null,"dnd_pipeline_scriptorium_transient_retries":null}'
 )
 
 cleanup() {
@@ -88,14 +91,37 @@ printf '%s\n' \
 baseline_log="$test_tmp/baseline.log"
 run_converge "$baseline_log" "${baseline_args[@]}"
 /usr/local/bin/seriatim --version
-/usr/local/bin/audita config validate --config /usr/local/etc/audita/config.yml
+AUDITA_LLM_API_KEY="$synthetic_audita_api_key" \
+  /usr/local/bin/audita config validate --config /usr/local/etc/audita/config.yml
+"$workspace_venv/bin/python" - <<'PY'
+import yaml
+
+with open("/usr/local/etc/audita/config.yml", encoding="utf-8") as config_file:
+    audita = yaml.safe_load(config_file)
+with open("/usr/local/etc/notarius/config.yml", encoding="utf-8") as config_file:
+    notarius = yaml.safe_load(config_file)
+with open("/usr/local/etc/scriptorium/config.yml", encoding="utf-8") as config_file:
+    scriptorium = yaml.safe_load(config_file)
+
+assert "transient_retries" not in audita["llm"]
+assert "repair_attempts" not in audita["llm"]
+assert "operation_timeout" not in audita["llm"]
+assert "transient_retries" not in notarius.get("promptkit", {})
+assert "transient_retries" not in scriptorium
+PY
 /usr/local/bin/notarius config validate --config /usr/local/etc/notarius/config.yml \
   --pipeline dnd-session
+/usr/local/bin/notarius config validate --config /usr/local/etc/notarius/config.yml \
+  --config-overlay testing --pipeline dnd-session
 notarius_effective_config="$test_tmp/notarius-effective.yml"
 /usr/local/bin/notarius config effective --config /usr/local/etc/notarius/config.yml \
   > "$notarius_effective_config"
+notarius_testing_effective_config="$test_tmp/notarius-testing-effective.yml"
+/usr/local/bin/notarius config effective --config /usr/local/etc/notarius/config.yml \
+  --config-overlay testing > "$notarius_testing_effective_config"
 grep -Fq 'mode: auto' "$notarius_effective_config"
 grep -Fq 'step: describe-session' "$notarius_effective_config"
+/usr/local/bin/scriptorium config validate --config /usr/local/etc/scriptorium/config.yml
 /usr/local/bin/scriptorium inspect profile --config /usr/local/etc/scriptorium/config.yml \
   --profile-dir "$profile_dir" --profile endpoint-profile
 /usr/bin/sudo -u narratio /usr/local/bin/narratio config validate \
@@ -103,26 +129,31 @@ grep -Fq 'step: describe-session' "$notarius_effective_config"
 /usr/bin/sudo -u narratio /usr/local/bin/narratio config validate \
   --config /usr/local/etc/narratio/pipeline.yml --campaign dilfs
 /usr/bin/sudo -u narratio /usr/local/bin/narratio config validate \
-  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --profile testing
+  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --overlay testing
 narratio_effective_config="$test_tmp/narratio-effective.yml"
 /usr/bin/sudo -u narratio /usr/local/bin/narratio config show \
   --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs \
   > "$narratio_effective_config"
+narratio_testing_effective_config="$test_tmp/narratio-testing-effective.yml"
+/usr/bin/sudo -u narratio /usr/local/bin/narratio config show \
+  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --overlay testing \
+  > "$narratio_testing_effective_config"
 grep -Fq 'enabled: true' "$narratio_effective_config"
-grep -Fq 'llm_api_key: AUDITA_LLM_API_KEY' "$narratio_effective_config"
 grep -Fq 'pipeline_id: dnd-session' "$narratio_effective_config"
-grep -Fq 'llm_api_key: OPENROUTER_API_KEY' "$narratio_effective_config"
 grep -Fq 'resume: true' "$narratio_effective_config"
 ! grep -Fq 'chunk_cache:' "$narratio_effective_config"
 grep -Fq 'party: narratio.input.party' "$narratio_effective_config"
 grep -Fq 'lane_id: item-registry' "$narratio_effective_config"
-"$workspace_venv/bin/python" - "$narratio_effective_config" <<'PY'
+"$workspace_venv/bin/python" - \
+  "$narratio_effective_config" "$narratio_testing_effective_config" <<'PY'
 import sys
 
 import yaml
 
 with open(sys.argv[1], encoding="utf-8") as config_file:
     config = yaml.safe_load(config_file)
+with open(sys.argv[2], encoding="utf-8") as config_file:
+    testing_config = yaml.safe_load(config_file)
 
 assert config["workspace"]["cleanup_after_publish"] is False
 assert config["storage"] == {
@@ -154,11 +185,21 @@ assert config["publish"] == {
         },
     ],
 }
+assert "config_overlay" not in config["notarius"]
+assert testing_config["notarius"]["config_overlay"] == "testing"
+assert all(
+    artifact["profile_id"] == "endpoint-profile"
+    for artifact in testing_config["scriptorium"]["artifacts"].values()
+)
+assert any(
+    artifact_id.startswith("character_meta_analysis_")
+    for artifact_id in testing_config["scriptorium"]["artifacts"]
+)
 PY
-! grep -Fq "$synthetic_audita_api_key" "$baseline_log" "$narratio_effective_config" "$notarius_effective_config"
+! grep -Fq "$synthetic_audita_api_key" "$baseline_log" "$narratio_effective_config" "$narratio_testing_effective_config" "$notarius_effective_config" "$notarius_testing_effective_config"
-! grep -Fq "$synthetic_notarius_api_key" "$baseline_log" "$narratio_effective_config" "$notarius_effective_config"
+! grep -Fq "$synthetic_notarius_api_key" "$baseline_log" "$narratio_effective_config" "$narratio_testing_effective_config" "$notarius_effective_config" "$notarius_testing_effective_config"
-! grep -Fq "$synthetic_object_storage_key_id" "$baseline_log" "$narratio_effective_config" "$notarius_effective_config"
+! grep -Fq "$synthetic_object_storage_key_id" "$baseline_log" "$narratio_effective_config" "$narratio_testing_effective_config" "$notarius_effective_config" "$notarius_testing_effective_config"
-! grep -Fq "$synthetic_object_storage_key" "$baseline_log" "$narratio_effective_config" "$notarius_effective_config"
+! grep -Fq "$synthetic_object_storage_key" "$baseline_log" "$narratio_effective_config" "$narratio_testing_effective_config" "$notarius_effective_config" "$notarius_testing_effective_config"
 /usr/bin/sudo -u narratio /usr/local/bin/narratio config artifacts \
   --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs | \
   awk -F '\t' '$1 == "session_recap" && $4 == "true" { found = 1 } END { exit !found }'
@@ -168,9 +209,6 @@ PY
 /usr/bin/sudo -u narratio /usr/local/bin/narratio config artifacts \
   --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs | \
   awk -F '\t' 'index($1, "character_meta_analysis_") == 1 && $4 == "false" && $7 == "character_meta_analysis" { found = 1 } END { exit !found }'
-/usr/bin/sudo -u narratio /usr/local/bin/narratio config diff default testing \
-  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs | \
-  awk -F '\t' '$1 != "changed" || $2 !~ /\.profile_id$/ { invalid = 1 } END { exit invalid || NR == 0 }'
 /usr/bin/sudo -u "$operator_user" /usr/local/bin/narratio config validate \
   --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs
 /usr/bin/sudo -u "$operator_user" /usr/local/bin/notarius config validate \
@@ -218,21 +256,6 @@ if run_converge "$invalid_key_log" "${baseline_args[@]}" \
   exit 1
 fi
 
-testing_profile_log="$test_tmp/testing-profile.log"
-run_converge "$testing_profile_log" "${baseline_args[@]}" \
-  -e 'dnd_pipeline_narratio_testing_scriptorium_profile=endpoint-profile'
-/usr/bin/sudo -u narratio /usr/local/bin/narratio config validate \
-  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --profile testing
-/usr/bin/sudo -u narratio /usr/local/bin/narratio config diff default testing \
-  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs | \
-  grep -F '"endpoint-profile"'
-/usr/local/bin/scriptorium inspect profile --config /usr/local/etc/scriptorium/config.yml \
-  --profile-dir "$profile_dir" --profile endpoint-profile
-testing_profile_repeat_log="$test_tmp/testing-profile-repeat.log"
-run_converge "$testing_profile_repeat_log" "${baseline_args[@]}" \
-  -e 'dnd_pipeline_narratio_testing_scriptorium_profile=endpoint-profile'
-require_clean_recap "$testing_profile_repeat_log"
-
 selected_version_log="$test_tmp/selected-version.log"
 run_converge "$selected_version_log" "${baseline_args[@]}" \
   -e 'dnd_pipeline_seriatim_version=v1.4.0'
@@ -242,24 +265,127 @@ run_converge "$selected_version_repeat_log" "${baseline_args[@]}" \
   -e 'dnd_pipeline_seriatim_version=v1.4.0'
 require_clean_recap "$selected_version_repeat_log"
 
-pipeline_group_one='{"archive-session":{"llm_profile":"dnd-extraction","input":{"module":"seriatim"},"artifacts":{"spells":{"extract":{"module":"dnd/spells"},"normalize":{"module":"dnd/spells"}}}}}'
+pipeline_group_one='{"archive-session":{"llm_profile":"gpt-luna-latest","input":{"module":"seriatim"},"artifacts":{"spells":{"extract":{"module":"dnd/spells"},"normalize":{"module":"dnd/spells"}}}}}'
-pipeline_group_two='{"research-session":{"llm_profile":"dnd-extraction","input":{"module":"seriatim"},"artifacts":{"spells":{"extract":{"module":"dnd/spells"},"normalize":{"module":"dnd/spells"}}}}}'
+pipeline_group_two='{"research-session":{"llm_profile":"gpt-luna-latest","input":{"module":"seriatim"},"artifacts":{"spells":{"extract":{"module":"dnd/spells"},"normalize":{"module":"dnd/spells"}}}}}'
-alternate_config="{\"notarius_pipeline_group_one\":$pipeline_group_one,\"notarius_pipeline_group_two\":$pipeline_group_two,\"dnd_pipeline_notarius_pipelines\":\"{{ notarius_pipeline_group_one | combine(notarius_pipeline_group_two) }}\",\"dnd_pipeline_narratio_notarius_pipeline_id\":\"archive-session\",\"dnd_pipeline_notarius_cache_chunk_plans_mode\":\"bypass\"}"
+alternate_config="{\"notarius_pipeline_group_one\":$pipeline_group_one,\"notarius_pipeline_group_two\":$pipeline_group_two,\"dnd_pipeline_notarius_pipelines\":\"{{ notarius_pipeline_group_one | combine(notarius_pipeline_group_two) }}\",\"dnd_pipeline_narratio_notarius_pipeline_id\":\"archive-session\",\"dnd_pipeline_notarius_testing_llm_profile\":\"gpt-terra-latest\",\"dnd_pipeline_notarius_cache_chunk_plans_mode\":\"bypass\"}"
 alternate_log="$test_tmp/alternate.log"
 run_converge "$alternate_log" "${baseline_args[@]}" -e "$alternate_config"
 /usr/local/bin/notarius config validate --config /usr/local/etc/notarius/config.yml \
   --pipeline archive-session
+/usr/local/bin/notarius config validate --config /usr/local/etc/notarius/config.yml \
+  --config-overlay testing --pipeline archive-session
 alternate_narratio_config="$test_tmp/alternate-narratio.yml"
 /usr/bin/sudo -u narratio /usr/local/bin/narratio config show \
   --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs \
   > "$alternate_narratio_config"
 grep -Fq 'pipeline_id: archive-session' "$alternate_narratio_config"
+alternate_testing_narratio_config="$test_tmp/alternate-testing-narratio.yml"
+/usr/bin/sudo -u narratio /usr/local/bin/narratio config show \
+  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --overlay testing \
+  > "$alternate_testing_narratio_config"
 alternate_effective_config="$test_tmp/alternate-effective.yml"
 /usr/local/bin/notarius config effective --config /usr/local/etc/notarius/config.yml \
   > "$alternate_effective_config"
-grep -Fq 'archive-session:' "$alternate_effective_config"
+alternate_testing_effective_config="$test_tmp/alternate-testing-effective.yml"
-grep -Fq 'research-session:' "$alternate_effective_config"
+/usr/local/bin/notarius config effective --config /usr/local/etc/notarius/config.yml \
-grep -Fq 'mode: bypass' "$alternate_effective_config"
+  --config-overlay testing > "$alternate_testing_effective_config"
+"$workspace_venv/bin/python" - \
+  "$alternate_narratio_config" "$alternate_testing_narratio_config" \
+  "$alternate_effective_config" "$alternate_testing_effective_config" <<'PY'
+import sys
+
+import yaml
+
+with open(sys.argv[1], encoding="utf-8") as config_file:
+    narratio_base = yaml.safe_load(config_file)
+with open(sys.argv[2], encoding="utf-8") as config_file:
+    narratio_testing = yaml.safe_load(config_file)
+with open(sys.argv[3], encoding="utf-8") as config_file:
+    notarius_base = yaml.safe_load(config_file)
+with open(sys.argv[4], encoding="utf-8") as config_file:
+    notarius_testing = yaml.safe_load(config_file)
+
+assert narratio_base["notarius"]["pipeline_id"] == "archive-session"
+assert "config_overlay" not in narratio_base["notarius"]
+assert narratio_testing["notarius"]["pipeline_id"] == "archive-session"
+assert narratio_testing["notarius"]["config_overlay"] == "testing"
+assert notarius_base["pipelines"]["archive-session"]["llm_profile"] == "gpt-luna-latest"
+assert notarius_testing["pipelines"]["archive-session"]["llm_profile"] == "gpt-terra-latest"
+assert notarius_testing["pipelines"]["research-session"]["llm_profile"] == "gpt-luna-latest"
+assert notarius_base["cache"]["chunk_plans"]["mode"] == "bypass"
+PY
 alternate_repeat_log="$test_tmp/alternate-repeat.log"
 run_converge "$alternate_repeat_log" "${baseline_args[@]}" -e "$alternate_config"
 require_clean_recap "$alternate_repeat_log"
+
+synthetic_fixture_audita_key='audita-override-synthetic-value'
+synthetic_fixture_notarius_key='notarius-override-synthetic-value'
+override_config="{\"dnd_pipeline_audita_backends\":{\"fixture\":{\"endpoint\":\"https://inference.fixture.invalid/v1\",\"credential\":\"FIXTURE_AUDITA_KEY\",\"concurrency\":2}},"\
+"\"dnd_pipeline_audita_profiles\":{\"fixture-proposal\":{\"id\":\"fixture-proposal\",\"backend\":\"fixture\",\"model\":\"fixture/proposal\",\"timeout_seconds\":900},"\
+"\"fixture-validation\":{\"id\":\"fixture-validation\",\"backend\":\"fixture\",\"model\":\"fixture/validation\",\"timeout_seconds\":900}},"\
+"\"dnd_pipeline_audita_llm_proposal_profile\":\"fixture-proposal\",\"dnd_pipeline_audita_llm_validation_profile\":\"fixture-validation\","\
+"\"dnd_pipeline_narratio_audita_credentials\":[\"FIXTURE_AUDITA_KEY\"],\"dnd_pipeline_narratio_notarius_credentials\":[\"FIXTURE_NOTARIUS_KEY\"],"\
+"\"dnd_pipeline_narratio_scriptorium_credentials\":[\"FIXTURE_AUDITA_KEY\",\"FIXTURE_NOTARIUS_KEY\"],"\
+"\"dnd_pipeline_audita_llm_transient_retries\":0,\"dnd_pipeline_audita_llm_repair_attempts\":0,\"dnd_pipeline_audita_llm_operation_timeout\":\"20m\","\
+"\"dnd_pipeline_notarius_promptkit_transient_retries\":0,\"dnd_pipeline_scriptorium_transient_retries\":0,"\
+"\"dnd_pipeline_secrets\":{\"AUDITA_LLM_API_KEY\":\"$synthetic_audita_api_key\",\"OPENROUTER_API_KEY\":\"$synthetic_notarius_api_key\","\
+"\"FIXTURE_AUDITA_KEY\":\"$synthetic_fixture_audita_key\",\"FIXTURE_NOTARIUS_KEY\":\"$synthetic_fixture_notarius_key\","\
+"\"OBJECT_STORAGE_KEY_ID\":\"$synthetic_object_storage_key_id\",\"OBJECT_STORAGE_KEY\":\"$synthetic_object_storage_key\"}}"
+override_log="$test_tmp/override.log"
+run_converge "$override_log" "${baseline_args[@]}" -e "$override_config"
+FIXTURE_AUDITA_KEY="$synthetic_fixture_audita_key" \
+  /usr/local/bin/audita config validate --config /usr/local/etc/audita/config.yml
+audita_override_settings="$test_tmp/audita-override-settings.yml"
+audita_override_profiles="$test_tmp/audita-override-profiles.yml"
+FIXTURE_AUDITA_KEY="$synthetic_fixture_audita_key" \
+  /usr/local/bin/audita config print-effective --config /usr/local/etc/audita/config.yml \
+  --view settings > "$audita_override_settings"
+FIXTURE_AUDITA_KEY="$synthetic_fixture_audita_key" \
+  /usr/local/bin/audita config print-effective --config /usr/local/etc/audita/config.yml \
+  --view profiles > "$audita_override_profiles"
+notarius_override_config="$test_tmp/notarius-override.yml"
+scriptorium_override_config="$test_tmp/scriptorium-override.yml"
+narratio_override_config="$test_tmp/narratio-override.yml"
+narratio_testing_override_config="$test_tmp/narratio-testing-override.yml"
+/usr/local/bin/notarius config effective --config /usr/local/etc/notarius/config.yml \
+  > "$notarius_override_config"
+/usr/local/bin/scriptorium config show --config /usr/local/etc/scriptorium/config.yml \
+  > "$scriptorium_override_config"
+/usr/bin/sudo -u narratio /usr/local/bin/narratio config show \
+  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs \
+  > "$narratio_override_config"
+/usr/bin/sudo -u narratio /usr/local/bin/narratio config show \
+  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --overlay testing \
+  > "$narratio_testing_override_config"
+"$workspace_venv/bin/python" - \
+  "$audita_override_settings" "$audita_override_profiles" \
+  "$notarius_override_config" "$scriptorium_override_config" \
+  "$narratio_override_config" "$narratio_testing_override_config" <<'PY'
+import sys
+
+import yaml
+
+settings, profiles, notarius, scriptorium, narratio, narratio_testing = (
+    yaml.safe_load(open(path, encoding="utf-8")) for path in sys.argv[1:]
+)
+assert settings["backends"]["fixture"]["endpoint"] == "https://inference.fixture.invalid/v1"
+assert settings["backends"]["fixture"]["concurrency"] == 2
+assert settings["llm"]["proposal_profile"] == "fixture-proposal"
+assert settings["llm"]["validation_profile"] == "fixture-validation"
+assert settings["llm"]["transient_retries"] == 0
+assert settings["llm"]["repair_attempts"] == 0
+assert settings["llm"]["operation_timeout"] == "20m0s"
+assert profiles["proposal"]["model"] == "fixture/proposal"
+assert profiles["validation"]["model"] == "fixture/validation"
+assert notarius["promptkit"]["transient_retries"] == 0
+assert scriptorium["transient_retries"] == 0
+assert narratio["audita"]["credentials"] == ["FIXTURE_AUDITA_KEY"]
+assert narratio["notarius"]["credentials"] == ["FIXTURE_NOTARIUS_KEY"]
+assert narratio["scriptorium"]["credentials"] == ["FIXTURE_AUDITA_KEY", "FIXTURE_NOTARIUS_KEY"]
+assert narratio_testing["scriptorium"]["credentials"] == ["FIXTURE_AUDITA_KEY", "FIXTURE_NOTARIUS_KEY"]
+PY
+! grep -Fq "$synthetic_fixture_audita_key" "$override_log" "$narratio_override_config"
+! grep -Fq "$synthetic_fixture_notarius_key" "$override_log" "$narratio_override_config"
+override_repeat_log="$test_tmp/override-repeat.log"
+run_converge "$override_repeat_log" "${baseline_args[@]}" -e "$override_config"
+require_clean_recap "$override_repeat_log"

tests/integration

@@ -22,6 +22,7 @@ baseline_args=(
   -e "dnd_pipeline_campaigns_revision=$campaigns_revision"
   -e "dnd_pipeline_prompt_library_repository_url=file://$prompt_library_repository"
   -e "dnd_pipeline_prompt_library_revision=$prompt_library_revision"
+  -e 'dnd_pipeline_notarius_testing_llm_profile=gpt-terra-latest'
   -e '{"dnd_pipeline_secrets":{"AUDITA_LLM_API_KEY":"audita-pipeline-synthetic-value","OPENROUTER_API_KEY":"notarius-pipeline-synthetic-value","OBJECT_STORAGE_KEY_ID":"object-storage-key-id-pipeline-synthetic-value","OBJECT_STORAGE_KEY":"object-storage-key-pipeline-synthetic-value"}}'
 )
 
@@ -62,14 +63,44 @@ fi
 baseline_log="$test_tmp/baseline.log"
 run_converge "$baseline_log"
 /usr/local/bin/seriatim --version
-/usr/local/bin/audita config validate --config /usr/local/etc/audita/config.yml
+AUDITA_LLM_API_KEY='audita-pipeline-synthetic-value' \
+  /usr/local/bin/audita config validate --config /usr/local/etc/audita/config.yml
+AUDITA_LLM_API_KEY='audita-pipeline-synthetic-value' \
+  /usr/local/bin/audita config print-effective --config /usr/local/etc/audita/config.yml \
+  --view profiles >/dev/null
 /usr/local/bin/notarius config validate --config /usr/local/etc/notarius/config.yml \
   --pipeline dnd-session
+/usr/local/bin/notarius config validate --config /usr/local/etc/notarius/config.yml \
+  --config-overlay testing --pipeline dnd-session
+notarius_testing_config="$test_tmp/notarius-testing.yml"
+/usr/local/bin/notarius config effective --config /usr/local/etc/notarius/config.yml \
+  --config-overlay testing > "$notarius_testing_config"
+/usr/local/bin/scriptorium config validate --config /usr/local/etc/scriptorium/config.yml
 /usr/local/bin/scriptorium inspect prompt \
   --config /usr/local/etc/scriptorium/config.yml \
   --prompt dnd.session_recap --prompt-version 2.0.0 --format json >/dev/null
 /usr/bin/sudo -u narratio /usr/local/bin/narratio config validate \
   --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs
+/usr/bin/sudo -u narratio /usr/local/bin/narratio config validate \
+  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --overlay testing
+narratio_testing_config="$test_tmp/narratio-testing.yml"
+/usr/bin/sudo -u narratio /usr/local/bin/narratio config show \
+  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --overlay testing \
+  > "$narratio_testing_config"
+"$workspace_venv/bin/python" - \
+  "$notarius_testing_config" "$narratio_testing_config" <<'PY'
+import sys
+
+import yaml
+
+with open(sys.argv[1], encoding="utf-8") as config_file:
+    notarius = yaml.safe_load(config_file)
+with open(sys.argv[2], encoding="utf-8") as config_file:
+    narratio = yaml.safe_load(config_file)
+
+assert notarius["pipelines"]["dnd-session"]["llm_profile"] == "gpt-terra-latest"
+assert narratio["notarius"]["config_overlay"] == "testing"
+PY
 
 repeat_log="$test_tmp/repeat.log"
 run_converge "$repeat_log"