The status page's walkthrough (M6.6b)

A new package, nisse-ui: a read-only page for studying how the agents
work. For each work item it shows the steps (what people and the
orchestrator said, and each run), each run's turns, and each turn's
request read against the log it was made from:
- each message beside the events it came from, tagged unchanged,
  labelled, narrated, shortened (by how much) or a compaction, with what
  fitting dropped;
- what is new since the turn before, and where the request first
  differs (where prompt reuse had to stop), next to the server's count;
- the reply with its reasoning, and the raw JSON.

Runs going in circles are flagged by nisse_core.loop.circles (repeated
near-identical replies, one correction given again and again, repeated
apologies), a pure function M7.8 can reuse in Driver.run.

In nisse-core:
- render.py: message_indexes(), from the same code render() uses, so
  the page's matching can't drift from what was sent.
- calls.py: the record notes when recording began; the reader gains
  calls_for(item) and call(id).
- state/readonly.py: opens an agent's SQLite file without creating its
  -wal/-shm files (mode=ro alone does, once the writer has closed).

The page reads only through read-only connections, escapes everything,
and sends a Content Security Policy that allows no script. It listens on
127.0.0.1; until M6.6d puts it behind Authelia, reach it over an SSH
tunnel. Jinja2 is its one new dependency, for autoescaping.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk

docs/Development-Plan.md

@@ -40,7 +40,7 @@ Only `nisse-dev` has real code; `nisse-core` and `nisse-ops` are placeholders.
 | **D3–D4** Workspace, git | partial | Idempotent publishing; no fresh workspace (#62), `git add -A` (#80) |
 | **D5** Review | partial | PR conversation comments only (#69), watch stall (#70) |
 | **D7–D8** Deployment, projects | partial | Bring-up runs `nisse-dev`'s and `nisse-review`'s images under systemd on this box; project entries in config (M1.4); egress not enforced |
-| **O**, **X** | partial | `nisse-dev` has its image (M1.5), `nisse-review` its own (M7.6, acceptance after merge); nothing runs on the agent host |
+| **O**, **X** | partial | `nisse-dev` has its image (M1.5), `nisse-review` its own (M7.6, acceptance after merge); nothing runs on the agent host; the status page's walkthrough runs on this box (M6.6b) |
 | `specs/` | done for now | `loop.qnt` (the architecture, #91); `orchestrator.qnt` went with `control.py` (M2.8) |
 
 ---
@@ -585,9 +585,11 @@ bring-up, end-to-end and benchmark runs; only d waits for M6.1.
 - **a. The call record** (L7) in `nisse-core`: written by the shared model client
   and `Driver.run`, with each message's provenance from the per-role view and
   fitting; wired in each agent's build; deleted at start. Each system prompt
-  says the calls are recorded, while they are.
+  says the calls are recorded, while they are. **Done** (#179).
 - **b. The walkthrough:** an item's steps, each run's turns, and each request read
-  against the log it was made from; runs going in circles flagged.
+  against the log it was made from; runs going in circles flagged. **Done** (this
+  PR): the `nisse-ui` package, on 127.0.0.1 behind an SSH tunnel until d. The
+  loop rules are `nisse_core.loop.circles`, for M7.8 to reuse.
 - **c. The overview:** each agent's active, queued, parked and blocked items.
 - **d. Deployment:** its image, the read-only mounts and a Caddy route behind
   Authelia (with #166).