Architecture: the general scope and the new-project sequence (for M2.5)

- L1: `general`, the scope of conversation not (yet) about a project: an
  item per thread, no repository, build VM or execution; closes after a day
  idle, a later reply starting a linked item.
- L5: every conversation is an item from its first message; chit-chat is
  answered, only work gets a Gitea issue.
- D1: a conversation's record issue is opened once it's work on a project.
  The new-project sequence: proposal, a provisioning checklist in Matrix,
  verified when the operator says done, a tracking issue carrying the
  distilled decisions (not the raw chat), then the architecture PRs.
- Q: a scratch build VM for general replaces the answered question about
  records for pure conversations.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE

docs/Development-Plan.md

@@ -184,9 +184,12 @@ between milestones (D2, D4). End-to-end: a two-milestone feature.
 - Deferred: a milestone with no changes that wasn't expected to change code is
   still raised with the operator (D4).
 
-**M2.5 Conversations and new projects.** *Needs discussion.* Work started in
+**M2.5 Conversations and new projects.** *Needs discussion;* the design was agreed
+in this PR (`general` scope, L1, L5; the new-project sequence, D1). Work started in
 conversation, record issues carrying their item's ID, the new-project flow and its
-project entry (D1, D8, #29). End-to-end: a small new project.
+project entry (D1, D8, #29). After M1.4. End-to-end: a small new project, in a
+repository the test operator creates under its own account for the run and
+deletes afterwards.
 
 **M2.6 Roles and capability profiles.** *Pre-approved.* `driver`, `helper`,
 `expert`, `classifier` (L9); escalation triggers; delegation and `ask_expert` on the