wicked-studio 0.6.8 → 0.7.0

package/README.md

@@ -22,9 +22,24 @@ reasoning in a scrollback you'll never read. wicked-studio flips that:
   work. Attention comes to *you* when a run hits a gate — you don't sit watching one terminal.
 - **Approve what matters.** Human-in-the-loop gates surface the real decisions (approve, approve
   with a steer, or reject) — with keyboard batch triage when several pile up.
-- **"Done" is proven, not claimed.** The evaluator is never the creator. Every run leaves
-  transcripts, diffs, and a downloadable evidence bundle; studio shows you the gate outcomes, it
-  never grades the work itself.
+- **"Done" is proven, not claimed — and the gate says how.** By default a run requires a distinct
+  evaluator and a judge: review goes to a seat other than the creator's. When no such seat exists, the
+  run stops at a gate that says why. You can then sign a second seat in, or relaunch with **reduced
+  assurance**, an explicit opt-in that the launch form and composer also offer on a one-seat roster.
+  A reduced run is labelled "Reduced assurance" on the session, every gate and the delivery. A team run
+  never grades on its creator's seat. A required judge that could not run holds its gate as "Waiting
+  for a judge seat"; it is not a rejection. A gate row or delivery whose evaluation the engine
+  recorded one for (wicked-core-ts 0.7.46 and later) shows the run's **assurance receipt**:
+  - what the run required and what actually ran;
+  - who built, evaluated and judged the work, and whether those were separate seats;
+  - what was skipped and why;
+  - the tree and the attempt.
+
+  So "Floor-only approval" reads differently from "Independently accepted". A post-hoc hand-over
+  that nothing re-verified is labelled "Unverified delivery", along with whether its tree moved, and
+  the delivery shows the QE acceptance check when the run requires one. Every run leaves
+  transcripts, diffs, and a downloadable evidence bundle. Studio shows you the gate outcomes; it never
+  grades the work itself.
 - **Understand the code first.** Onboard a repo and studio builds its graph — then blast-radius
   for any symbol, hotspots, the domain/requirements view, and a searchable map of what calls what.
 
@@ -33,19 +48,29 @@ reasoning in a scrollback you'll never read. wicked-studio flips that:
 - **Run governed agents on your repos** — register a local path or clone a URL; studio builds the
   code graph, then you launch runs (ask / balanced / autonomous), pick which agent seats join, and
   bind a repo with optional PR delivery.
-- **Steer runs live** — a real-time timeline of every run, human gates with approve / steer /
-  reject, elicitation prompts, pre-gate guidance notes, and lifecycle controls (cancel, inject a
-  message, retry).
+- **Steer runs live** — the Desk (the one shell) puts what needs you first; every run or chat
+  opens as a **session** (`/s/:id`): one thread with the live record, gate rows you answer in place
+  (approve / steer / reject), elicitation prompts, pre-gate guidance notes, and lifecycle controls
+  (cancel, inject a message, retry). Old `/runs/:id` links redirect to the session.
 - **See the evidence** — per-step transcripts, a worktree file + diff viewer, and one-click
   evidence-bundle download for any run.
 - **Explore your codebase** — graph view with focus navigation, blast radius, hotspots, and the
   domain graph with coverage.
-- **Ask your whole model roster at once** — fan one question out to every warm CLI and compare the
-  answers side by side.
+- **Plan the product** — the **Product** view (rail → Product, `/product?project=<id>`) answers
+  "what are we building" where the Desk answers "what is executing". It lists a project's
+  requirements across every one of its repositories, grouped by repo and searchable; a repo that
+  could not be read is named with the reason. Choose up to 40 requirements and an optional steer,
+  and **Draft epics** launches a governed draft → review → approve run that opens in its session;
+  its plan and gate are answered there. Coverage and the domain model stay on the project page.
+  Publishing the drafted epics is not offered yet.
+- **Ask several seats at once** — a chat can hold more than one warm CLI seat; each answers in the
+  thread, and the daemon checks every path, `path:line` and commit a reply cites against the repo.
 - **Govern the work** — author steering rules and policies, browse the decisions ledger, and review
   what the platform has learned about your repos.
-- **Work in projects** — group repos, runs, chats, and docs; a merged activity feed and dashboard
-  per project; deep-linkable routes throughout.
+- **Work in projects** — group repos, runs, chats, and docs; "See everything" (`/everything`) lists
+  them, filterable by project, and a project's address (`/p/:id`) opens its scoped Sessions list;
+  deep-linkable
+  routes throughout.
 - **Plus** governed terminals, a Cmd+K command palette, document & video creation modes, and
   desktop notifications when a run needs you.