fix(aligned-onboarding): preserve full creative summaries

.github/workflows/validate-catalog.yml

@@ -1,6 +1,7 @@
 name: Validate
 
 # Structural gates for OS packages and the rebuilding-page site:
+#   test-aligned-onboarding — full-fidelity creative-corpus export
 #   validate-package-index — package registry and manifest contract
 #   build-site             — typecheck + build use-case-library-site
 
@@ -17,6 +18,16 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  test-aligned-onboarding:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+      - name: Test the Aligned Onboarding creative-corpus exporter
+        run: node --test aligned-onboarding/test/export-creative-corpus.test.mjs
+
   validate-package-index:
     runs-on: ubuntu-latest
     steps:

README.md

@@ -54,6 +54,12 @@ legacy directory directly.
 the recently merged onboarding flow keeps its source and referenced
 dependencies while it is migrated to the package contract.
 
+Validate its deterministic creative-corpus export with:
+
+```bash
+node --test aligned-onboarding/test/export-creative-corpus.test.mjs
+```
+
 ## Library website
 
 `use-case-library-site/` remains deployed as a rebuilding page. Its archived

aligned-onboarding/README.md

@@ -23,7 +23,9 @@ files: they do different jobs, persist to different places, and refresh on diffe
 These instruction files (this overview, the Account Context Brain, the Creative Corpus, and the
 Motion CLI Data-Query Guide) are the package itself, not its output. They live in the Brain outside
 the `meta` folder structure; the exact folder for them is not fixed yet and can be decided later.
-corpus-search is a bundled tool, not an instruction file, and installs under
+The deterministic creative-corpus exporter installs with the orchestration skill at
+`/agent/.agents/skills/aligned-onboarding/bin/export-creative-corpus.mjs`. corpus-search is a
+bundled tool, not an instruction file, and installs under
 `/agent/tools/corpus-search/`. The `meta` folder holds only what Runneth generates from running the
 package: the filled account context and the per-creative files.
 
@@ -64,12 +66,17 @@ File: `account-context-brain.md`
 ### Creative Corpus
 File: `creative-corpus-playbook.md`
 
-- **Job:** build and maintain one enriched record per active creative (identity, summary, hook,
-  value props, transcript, AI tags, naming), the attributes Runneth uses to do the analysis the
-  Account Context Brain defines.
+- **Job:** build and maintain one enriched record per active creative (identity, complete ad
+  description, complete hook/headline, creative breakdown, messaging and positioning, transcript,
+  AI tags, naming), the attributes Runneth uses to do the analysis the Account Context Brain
+  defines.
 - **How it runs:** reads what the Account Context Brain already knows, then pulls from Motion only
-  what the Account Context Brain cannot tell it (the creative content itself). No separate corpus
-  tool to install.
+  what the Account Context Brain cannot tell it (the creative content itself). The installed
+  exporter validates and writes the raw sections deterministically; it never selects only the first
+  hook or reduces the creative breakdown and messaging to a few fields. Replacement exports
+  resolve by stable `source_id`, preserve missing prior Motion enrichment, and retain a protected
+  Account Context projection containing decoded naming and custom-threshold Spend State across
+  ad-name changes.
 - **Persists to:** individual creative Markdown files under `/agent/brain/meta/creatives/`, plus an
   optional tagging taxonomy at `/agent/brain/meta/creatives/_tagging-taxonomy.md`.
 - **Retrieval:** automatic through Knoweth. Writing the file is the index step.
@@ -122,9 +129,14 @@ similar. Everything shares one index, kept separate by the `kind` tag (`creative
 4. **Install corpus-search.** Run `bash /agent/tools/corpus-search/install.sh`, resolve its
    checklist (including `OPENAI_API_KEY`), and register `/agent/brain/meta/creatives` as a source
    with `kind: creative`. One-time; can happen before or after the corpus is built.
-5. **Build the Creative Corpus.** With the Account Context Brain in place, generate the per-creative
-   attribute files (each with its frontmatter). The Creative Corpus reads the Account Context Brain
-   for interpretation. Then index the folder into corpus-search so filterable search is available.
+5. **Build the Creative Corpus.** With the Account Context Brain in place, request all four Motion
+   summary sections and run the installed exporter to generate the per-creative attribute files
+   (each with its frontmatter). Project decoded naming and custom-threshold Spend State into each
+   file's protected Account Context block; the exporter preserves that block on later full or
+   fully enriched scoped replacements. Existing records resolve by `source_id`, so ad-name drift
+   moves one record, and omitted retry enrichment retains the prior complete Motion sections. The
+   Creative Corpus reads the Account Context Brain for interpretation. Then index the folder into
+   corpus-search so filterable search is available.
 6. **Keep both current.** The Account Context Brain on its refresh cadence, the Creative Corpus on
    daily and event-triggered maintenance, and refresh the corpus-search index on that same cadence.
 

aligned-onboarding/SKILL.md

@@ -36,6 +36,8 @@ procedures live in the staged docs and are the source of truth for each step:
 - Account Context Brain: `/agent/brain/aligned-onboarding/account-context-brain.md`
 - Creative Corpus playbook: `/agent/brain/aligned-onboarding/creative-corpus-playbook.md`
 - Motion CLI data-query guide: `/agent/brain/aligned-onboarding/motion-cli-data-query-guide.md`
+- Creative Corpus exporter:
+  `/agent/.agents/skills/aligned-onboarding/bin/export-creative-corpus.mjs`
 
 ## Scope rules (apply throughout)
 
@@ -66,9 +68,18 @@ procedures live in the staged docs and are the source of truth for each step:
    install-config; never clobber a customized copy. It supplements Knoweth for deliberate,
    filterable search. Register `/agent/brain/meta/creatives` as a source with `kind: creative`.
 5. **Build the Creative Corpus.** Follow `creative-corpus-playbook.md`: read what the Account
-   Context Brain already knows, pull only the creative content from Motion, and write one enriched
-   Markdown file per active creative under `/agent/brain/meta/creatives/`. Writing the files is the
-   index step for Knoweth; index the corpus-search source too if installed.
+   Context Brain already knows, request all four Motion summary sections (`adDescription`,
+   `hookOrHeadline`, `creativeBreakdown`, and `messagingAndPositioning`), then run the installed
+   exporter over the returned Motion JSON. Do not hand-select nested fields. The exporter writes one
+   enriched Markdown file per active creative under `/agent/brain/meta/creatives/` and fails on a
+   malformed non-null section. Project the Account Context Brain's decoded naming and
+   custom-threshold Spend State inside each file's protected Account Context block; later exports
+   find the record by stable `source_id` and preserve that block across ad-name changes. If a
+   transcript needs a scoped retry, request all four summaries, glossary, metrics, and transcript
+   together, then export that fully enriched result after the full pull. Never export a
+   transcript-only result. If Motion omits requested retry enrichment, the exporter preserves the
+   prior complete Motion sections by `source_id` or fails before writing when none exists. Writing
+   the files is the index step for Knoweth; index the corpus-search source too if installed.
 6. **Keep both current.** Account Context Brain on a monthly-plus-drift cadence; Creative Corpus on
    daily and event-triggered maintenance. Log every refresh in `/agent/brain/meta/_changelog.md`.