M8: the browser becomes the storyteller

The interface was AI-DnD's with this product's features bolted into it. The
navigation read Home · Adventures · Scenarios · Settings · AI Chat; starting a
story meant first picking a *world*, and making a world meant a JSON stat-schema
form, a story-card table and an art picker. The play screen had a Branches tab.
The input had three modes. Sixteen of the sixteen controls on a two-turn story
had no accessible name — they were single glyphs with a tooltip.

All of that was measured in a real browser before anything was changed, and the
measurements are in planning/reports/M8-IMPLEMENTATION-REPORT.md §C. Almost
nothing underneath was wrong: the play loop, the history controls, the takes,
the Save Points, the state correction and the knowledge library all worked. What
was wrong was what a reader was asked to understand in order to use them.

So the shape now is one entry point and one screen:

  Campaigns -> Campaign -> Story
                           State · Knowledge · Context · Save Points · Settings

Everything that is not the story lives in a panel that starts closed. The
top navigation bar is hidden on the story screen entirely, because on that one
screen the story is the interface.

Play is one natural-language field. An action and a piece of quoted dialogue are
both just what the reader wrote, and B01/B02 confirmed against a real narrator
that the model reads the quotes without being told which kind of turn it is.
What survives from the old Story mode is a Story direction toggle, which is not
a fourth mode: it changes who is being spoken to, not what kind of action is
taken, and the box is visibly marked while it is on.

Branch, fork, node, merge and head appear nowhere a reader can see them. The
branch panel and the tree overlay are gone from the browser. The mechanism is
untouched — takes, divergence, retained futures and Save Points all still work,
and their endpoints are still tested. This is a decision about what a reader is
asked to understand, not a reduction of what the product can do.

The two defects worth the space:

A player action is stored with AI Dungeon's "> You " prefix. That was right when
the Do mode asked for a bare verb phrase. With one field the spec tells the
reader to write "I enter the tavern", and the result was "> You I enter the
tavern." — in the transcript, in the replayed history, and therefore in the
narration, where a small model imitates it and writes "You I thank her". M8's
own design surfaced it, so M8 fixed it: the prefix is added only when the reader
has not already written a subject. The ">" marker, which is what actually
identifies a player turn in the prompt, is unchanged in every case.

And a stale `.input-bar { display: flex }` in play.css overrode the new
composer, because that sheet is imported after the new one. The direction row
and the input row laid out side by side and the box was unusably narrow. Found
by opening the product in a browser, not by reading the CSS — which is the
argument for having done that first.

Failures now have the taxonomy the spec asked for rather than one toast: model,
generation, state, knowledge, server, each with the thing to do about it. A
failed turn leaves the reader's words in the box and says so. The classification
reads backend strings, so it is a fallback ladder rather than a lookup — an
unrecognised message still classifies, still shows the server's own words and
still offers Retry.

`Settings.model` could be empty with nothing saying so until the first turn
failed with a provider error. The header now reports Ollama in five states, and
an unconfigured or missing model offers the models actually installed on the
endpoint, from the connection test that already knew them. Nothing is chosen
automatically: an endpoint's first model may be an embedding model, which cannot
narrate at all.

Narrator prose is rendered as safe Markdown — headings, emphasis, lists,
blockquotes, code. The safety is structural rather than filtered: every node is
a React element built from parsed text, and there is no dangerouslySetInnerHTML
in the file. A sanitizer is not needed to make markup safe if markup is never
produced from input. Link schemes are checked with the URL parser rather than a
pattern, because the bypasses are all in the parsing. A remote image is a
placeholder naming the blocked address; the knowledge and context panels
deliberately do not use this renderer at all, because they exist to show a
reader exactly what is in their file.

Backend, and only what the browser could not otherwise reach:

  AdventureCreate.opening   a start action could only come from a Scenario, so
                            every campaign made in the new setup flow opened on
                            a blank page. Same node, same code path.
  canon_rules               campaign_canon has been the highest authority in a
                            campaign since M5, read by the prompt builder and
                            the state validator, and had no API at all — a
                            fixture had to write it with SQL.
  a 401 and a 429 message   the last user-facing text describing a hosted
                            deployment. One told the reader to check an API key
                            that has not existed since M2.

No schema change and no migration: proved by building a database with a server
running the M7 commit's own code and opening it with this one.

The project had no frontend tests. It has 132 now, across ten files, running
in about six seconds — the enabled state of every history control, the take
selector, the confirmations, the panels, the five model states, the failure
taxonomy, the focus trap, accessibility, and that the reserved dictation control
never touches the microphone. Writing them found a real defect: the focus trap
filtered candidates with offsetParent, which is null inside the fixed-position
ancestor the dialog has and which jsdom never computes — it would have behaved
differently in the tests from the browser.

They do not replace the real-browser runs, and both kinds of evidence are in the
report. The browser suites drive the production build served by the real backend
with a real local narrator, including a genuine process restart.

A verification pass over all of it then found three more, each by driving the
product rather than reading it:

Stepping between alternate takes did nothing. The pager asked whether a take
lived on another line by comparing `target.branch_id !== action.branch_id`, and
`ActionOut` has never carried `branch_id` — so the comparison was permanently
`number !== undefined`, always true, and every step took the branch-switch path.
For two takes of an ordinary retry, which share a line until one is written
below, that meant switching to the line already being read: the same window came
back and nothing moved. D07 is a required v1 acceptance test. The fix needed no
new field — the variants list already carries every attempt's branch and marks
the live one.

The first regression test for that passed against the broken code, because its
fixture gave the action a `branch_id` the real payload never sends. That is the
exact failure M7's review was about, so the fixture was corrected, the tests were
re-run against the reverted code and failed for the right reason, and the
fixture now carries a docstring saying why the field must never come back.

And the knowledge panel pointed readers at an "embedding model" while the
setting is called "Model for meaning-based search" — a reader sent looking for a
field that does not exist by that name.

Campaign canon was measured rather than assumed. Editing it after play is a
configuration change: every turn already played keeps the canon it was actually
given, in its own context snapshot, and the accepted story, the state document
and the state audit log are byte-identical across an edit. It is not routed
through M5's state audit, because canon is not narrative state and doing so
would create the second representation the spec forbids. What the editor does
now is say so, once a campaign has moments.

`BROWSER-UX-SPEC.md` §38 asked for a "Show Hidden Story State" toggle. There is
no hidden story state — a secret lives in a narrator-only knowledge source and
never enters the state document. The section is rewritten to require what it
actually meant: ordinary surfaces must not carry narrator-only information,
advanced inspection must withhold it by default behind an explicit warned
choice, and no second store may be invented to give a toggle something to
reveal. The protection is stricter than before, not weaker.

Closeout. An independent review returned M8 IMPLEMENTATION: PASS subject to
evidence and documentation cleanup, and this commit carries that cleanup:

The report named two frontend bundles as the artifact behind its acceptance
evidence. The saved run logs settle it. index-Ii-lARp9.js, built at 18:53:02
from this tree, is the one final frozen artifact behind all 157 browser checks;
index-C6E5Uvtu.js is superseded — it predates the D09 fix and its acceptance
suite ended 54/55 on exactly that defect. No tracked file under backend/app or
frontend/src has a modification time after the freeze, so the whole final
campaign describes one build. §P sets the two side by side.

Finding 14 — the app budgets 16,384 prompt tokens while an Ollama that sees no
VRAM enforces 4,096 — is resolved operationally, with no application change.
The OpenAI-compatible endpoint this app speaks accepts num_ctx and ignores it,
and reloads the model at its own default, so a native call cannot prime it
either. A model derived with POST /api/create carries the parameter, is honoured
through the app's own OpenAI-compatible path, and appears in /v1/models — which
is the listing the Settings model picker already reads. Measured end to end.
The procedure is in DEVELOPMENT.md; nothing in the repository depends on any
particular derived model existing. Adding provider code to work around this was
declined deliberately: it would mean either a second native request path,
against ADR 011, or a parameter the endpoint provably ignores.

The §38 rewrite is ratified as a requirement clarification aligned with the
implemented architecture, and the spec gains the clause finding 3 was really
about: withheld material must be absent from the rendered DOM, not merely
collapsed in it.

The report's §U carries the M9 handoff — what a portable campaign has to include,
whether historical context snapshots belong in the bundle, what happens to
inherited story cards, and that a restored campaign may meet a different context
window than the one that wrote it. None of it is implemented here.

Final: backend 950 passed / 14 skipped; frontend 132 passed; lint, production
build and Docker build clean; 157 browser checks across six suites, zero
failures. M8 is implemented, verified, reviewed and accepted (2026-09-06).
M9 has not been started.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017HdaXiFbscatQaLS7dJk6b

planning/BROWSER-UX-SPEC.md

@@ -184,6 +184,15 @@ unless inherited UI makes them useful without complexity.
 
 Optional helpers may exist.
 
+### As implemented in M8
+
+One field. The inherited `Do` / `Say` / `Story` selector is gone: an action and
+a piece of quoted dialogue are both just what the reader wrote, and B01/B02
+confirmed against a real narrator that the model reads the quotes without being
+told. What survived from `Story` mode is the direction toggle in §13, which is
+deliberately not a fourth mode — it changes who is being spoken to, not what
+kind of action is taken.
+
 ## 13. Out-of-Character Direction
 
 The user should have a way to provide story-direction instructions.
@@ -468,6 +477,21 @@ Open Threads
 
 Keep concise.
 
+### As implemented in M8
+
+The server groups the state and the panel renders the groups, so the section
+headings are whatever the campaign has established rather than a fixed list —
+a campaign with no items shows no Items heading. Nothing is rendered as JSON,
+and each row offers **Correct** and, for a fact, **That's wrong**.
+
+**There is no hidden dimension in the narrative state**, so there is nothing
+here to reveal. A secret never enters authoritative state: it lives in a
+knowledge source marked narrator-only, which the narrator is told not to
+disclose. M7 verified against a real narrator that the secret stays out of the
+state document. §38's requirement is met by this panel simply not containing
+narrator-only information; the surface that must actively withhold it is the
+context inspector — see §57.
+
 ## 32. Current Scene Section
 
 Show:
@@ -544,19 +568,44 @@ Visual profile
 
 Advanced data may be hidden behind expandable sections.
 
-## 38. Hidden Narrator State
+## 38. Hidden Narrator Information / Spoilers
 
-Some campaigns may contain secrets.
+Some campaigns contain secrets the narrator knows and the protagonist does not.
 
-Normal player-facing state panel should not reveal narrator-only facts by default.
+The requirement is:
 
-Provide optional advanced mode:
+- ordinary State and story surfaces must not expose narrator-only information;
+- an advanced inspection surface that can contain hidden Canon or narrator-only
+  context must **withhold it by default**;
+- revealing it requires an explicit, clearly labelled user action;
+- the UI must warn that doing so may reveal campaign secrets;
+- withheld material must be **absent from the rendered DOM**, not merely
+  visually collapsed — a closed `<details>`, a `hidden` attribute or a
+  `display: none` rule still leaves the text findable by browser search, by the
+  accessibility tree and by anyone reading the page source;
+- **no second hidden-state store or duplicate representation** may be introduced
+  solely to give the UI something to toggle.
 
-```text
-Show Hidden Story State
-```
+### Where the secret actually lives (ratified at M8)
 
-with clear warning.
+This section originally described a `Show Hidden Story State` control on the
+state panel. That named the wrong surface, and M8's review ratified the
+correction.
+
+Narrator-only material is not held in the narrative state. It is held in the
+knowledge/canon system, as a source marked narrator-only, and the narrator is
+instructed not to disclose it. A secret therefore never enters the state
+document at all — M7 verified that against a real narrator — so a toggle on the
+state panel would reveal nothing, and building a hidden-state dimension to give
+it something to reveal would create exactly the duplicate representation the
+requirement above forbids.
+
+The surface that genuinely needs protecting is **advanced context inspection**,
+because a retrieved narrator-only passage is reachable there. That is where the
+default-withheld behaviour belongs, and where §57 records it as implemented.
+
+The vocabulary for this is **hidden-information inspection** — not
+"hidden-state", which implies a state subsystem that does not exist.
 
 ## 39. Campaign Sidebar / Menu
 
@@ -824,6 +873,14 @@ Optional advanced tab:
 Rendered Prompt
 ```
 
+### As implemented in M8
+
+The M7 panel opened on 11,996 characters of assembled prompt. The M8 panel opens
+on the same campaign at about 1,400: token usage, then what the narrator read,
+what the story remembered, the summary, how much history was sent, and what
+produced it — each collapsible. The assembled prompt is the last section and is
+closed.
+
 ## 56. Retrieved Memory Row
 
 Example:
@@ -864,6 +921,25 @@ answer rather than a silence.
 Click-to-open-source is not implemented; the Knowledge panel is one click away
 and lists the same file.
 
+### As implemented in M8
+
+Click-to-open-source **is** implemented: the row carries `source_id`, and the
+filename is a button that opens the Knowledge panel on that source rather than
+on the list.
+
+The rows were also rewritten to read rather than to enumerate — `found by
+hybrid · closeness 0.71 · 40 tokens` in place of a run of raw scores — and the
+class tag is now the same component the Knowledge panel uses, so a class looks
+the same wherever a reader meets it.
+
+**Narrator-only passage text is withheld by default.** This is where §38's
+hidden-information requirement actually lands: the only place a campaign's secrets are
+reachable from an ordinary screen is a retrieved passage that was marked
+narrator-only. The row shows the file, the class and the badge, and the text is
+replaced by *"Hidden — this passage is narrator-only"* until the reader ticks a
+control that says what it will reveal. Turning it on is a preference in that
+component and nothing else: it changes no retrieval, no prompt and no state.
+
 The passage text is rendered as a text node in a `<pre>`, never as markup. That
 is where H06 and H07 are decided for imported content, and it is the reason a
 Markdown renderer was not added here for appearance.
@@ -1432,7 +1508,7 @@ The final v1 browser interface must support:
 - collapsible state panel,
 - direct entity inspector,
 - token usage display,
-- hidden-state inspector,
+- spoiler-aware advanced inspection of hidden narrator information,
 - knowledge retrieval provenance,
 - clear local-only status.