The contained runner that drove the 2026-09 security audit, the README
review and four rounds of design ideation lived only inside the ignored
notebook. It moves to scripts/agent-runner/: the prepare, tools, audit,
ideation and teardown scripts, the compose and container files, the
allowlist proxy and the prompt templates, with the paths that assumed
the notebook fixed and findings written to a caller-named directory. Run
outputs, transcripts and the round-specific sheet scripts stay behind.
docs/agent-runner.md states the method: the disposable git archive
copy and the fail-closed proxy, how a task is shaped, union rather than
intersection of findings across models, separate adjudication of every
finding against the source, and the evidence a finding must carry.
The exploration directory held 245 tracked files, and one week's
notebook had grown to 28M of captures, per-run CSS copies and model
logs, so every change ended with an argument about what to prune. It is
now a local lab notebook: git ignores it, its tracked files are
untracked, and no tracked file cites a path under it, because another
clone does not have it.
Every live citation is rewritten so the fact stands in the sentence:
the docs pages, AGENTS.md, four main specs, one Go comment, issues.md
and milestones.md. The operator IA page gains the landed IA revisions it
used to point at, and the UX rubric moves to docs/first-contact-rubric.md
because the process requires it. Archived changes, status/archive,
status/log and design/ keep their old paths as frozen history; the
design/ ones are logged as an upstream issue. MAINTAINING.md and the
status README describe the notebook and the harvest that replaces
pruning.
Parse every config value through a single declared type at save, boot,
and validate, and expose the settings seam from the terminal so
operators can list, set, clear, and validate overrides without SQL.
- Add shared ui_*.html parts (pageHeader, sectionHeader, statusBadge,
emptyState) parsed into every template set
- Add anatomy lint rules with a shrinking allowlist and screen-coverage
check
- Add make screens capture harness with contact sheets and baseline diff
- Compose member and FedWiki regions server-side so pages arrive
complete
- Rebuild Domains and Integrations on the parts as pilots
Move settled investigation records into
`status/explorations/<topic>-<date>/` with README indexes,
promote durable conventions to `docs/`, and add
`docs/identifiers.md` plus upstream Doc 46 person-name
provenance documents. Update cross-references and archive
resolved issues.
Implement the ux-first-run change: a state-derived setup checklist on
/operator/setup with a landing region that recedes once required steps
are done, and empty states that distinguish blocked from empty across
operator and member surfaces. Also add production deployment and
environment reference docs, plus a config-key completeness test.
Introduce `docs/models/` with the catalog index and its first card
(product-catalog), recording invariants, dimensions, and drift traps
per the Decision 141 documentation division. Add the model-cards
openspec change (proposal, design, spec, tasks) and sync the design
docs to v15: product kind taxonomy dissolved (Decisions 134–139),
Decisions 140–141 ratified, and product/pricing helpers updated. The
catalog is the single descriptive home for as-built models.
Clarify provider vs integration terminology and document the in-tree
distribution model. Refresh M9 status, issue tracking, and lint/doc
links to
use the new language.
Rewrite the README around purpose, architecture, quickstart, and
status. Add contributing/security policies plus a docs index with
audience front matter across existing docs.
cgalo5758