Rewrite docs and READMEs in Google developer documentation style

Trim em dashes, convert first-person plural to second person, and
tighten sentences in README.md, docs/GUIDE.md, docs/self-review.md,
and frontend/README.md, matching the style already applied to code
comments. No technical content, numbers, or code blocks changed.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N7vUFpYkLrJnuSgwcRjqSx

README.md

@@ -3,76 +3,77 @@
 [![CI](https://github.com/parththakkar106/AI-DnD/actions/workflows/ci.yml/badge.svg)](https://github.com/parththakkar106/AI-DnD/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 
-An AI Dungeon-style interactive storytelling app you can run entirely on your own machine —
+An AI Dungeon-style interactive storytelling app that runs entirely on your own machine, with
-with your own AI model. Create scenarios, play open-ended adventures where an LLM narrates the
+your own AI model. Create scenarios, play open-ended adventures where an LLM narrates the
 world, and extend the engine with **JavaScript scripts compatible with real AI Dungeon
 scripting**.
 
 > ### ▶️ Try it live: **[parththakkar106.github.io/AI-DnD](https://parththakkar106.github.io/AI-DnD/)**
-> The project page loads instantly and launches the hosted demo in one tap — play a scenario as
+> The project page loads instantly and launches the hosted demo in one tap. Play a scenario as
-> a guest, no sign-up and no API key needed. (The demo runs on a free tier that sleeps, so the
+> a guest: no sign-up and no API key needed. The demo runs on a free tier that sleeps, so the
-> first load after it's been idle takes ~30–60s to wake up.)
+> first load after it's been idle takes about 30 to 60 seconds to wake up.
 >
-> Want the internals? The **[design notes](https://parththakkar106.github.io/AI-DnD/guide.html)**
+> For the internals, read the **[design notes](https://parththakkar106.github.io/AI-DnD/guide.html)**.
-> walk through the context budgeting, the world-state referee and the memory bank, and state the
+> They walk through the context budgeting, the world-state referee, and the memory bank, and
-> reasoning behind each one ([Markdown version](docs/GUIDE.md)).
+> state the reasoning behind each one ([Markdown version](docs/GUIDE.md)).
 
-Built with FastAPI + SQLAlchemy on the backend and React (Vite) on the frontend, running on
+Built with FastAPI and SQLAlchemy on the backend and React (Vite) on the frontend, running on
-SQLite locally and Postgres in the cloud. Works with **any OpenAI-compatible endpoint**: Ollama
+SQLite locally and Postgres in the cloud. It works with **any OpenAI-compatible endpoint**:
-and LM Studio locally, or OpenRouter / OpenAI / Groq / vLLM in the cloud — endpoint, key, and
+Ollama and LM Studio locally, or OpenRouter, OpenAI, Groq, or vLLM in the cloud. Endpoint, key,
-model are all runtime settings, and OpenRouter's free-tier models make the whole experience $0.
+and model are all runtime settings, and OpenRouter's free-tier models make the whole experience
+cost nothing.
 
 ![The play screen, with the world-state rail open](docs/images/play-world-state.jpg)
 
-*The play screen. The left rail is live world state — the AI proposes changes each turn and a
+*The play screen. The left rail shows live world state. The AI proposes changes each turn, and
-Python engine decides what actually sticks. The chip under the narration reports what changed.
+a Python engine decides what actually sticks. The chip under the narration reports what
-The `‹ 2/2 ›` under a turn steps between the takes it has; writing below one that isn't the
+changed. The `‹ 2/2 ›` under a turn steps between the takes it has. Writing below a take that
-live one is what starts a new branch.*
+isn't the live one starts a new branch.*
 
 ## Features
 
-- **The full play loop** — Do / Say / Story / Continue actions, streamed AI responses (SSE),
+- **The full play loop.** Do / Say / Story / Continue actions, streamed AI responses (SSE),
-  retry, undo, and edit. Reasoning models supported: "thinking" streams into a collapsible 💭
+  retry, undo, and edit. Reasoning models are supported: "thinking" streams into a collapsible
-  panel with its own token budget.
+  💭 panel with its own token budget.
-- **A branching story tree** — the story is a tree, not a list. Any turn can hold more than one
+- **A branching story tree.** The story is a tree, not a list. Any turn can hold more than one
-  **take**; `‹ 2/4 ›` steps between them, and stepping is free — the story below simply empties,
+  **take**, and `‹ 2/4 ›` steps between them. Stepping is free: the story below simply empties,
-  and the server is told nothing. **Writing below a take that isn't the live one is what makes a
+  and the server is told nothing. Writing below a take that isn't the live one is what makes a
-  branch.** Branches borrow their ancestors' turns instead of copying them, so a fork costs about
+  branch. Branches borrow their ancestors' turns instead of copying them, so a fork costs about
-  100 bytes and a 20-fork story loads within 1% of the same story flat; switching restores that
+  100 bytes, and a 20-fork story loads within 1% of the same story flat. Switching restores that
-  line's world state, script state and cooldown clocks. A branch panel switches, renames and
+  line's world state, script state, and cooldown clocks. A branch panel switches, renames, and
   deletes; **⌗ See the tree** draws every line against the story's own clock
   (`backend/app/tree.py`, `backend/app/context/lineage.py`).
-- **An RPG world-state engine** — a scenario can declare stats, flags, milestones and a named
+- **An RPG world-state engine.** A scenario can declare stats, flags, milestones, and a named
-  cast; the adventure carries their live values. The design is **the AI proposes deltas and a
+  cast; the adventure carries their live values. The AI proposes deltas, and a Python engine
-  Python engine referees them**: it clamps to range, enforces per-turn caps and cooldowns, keeps
+  referees them: it clamps values to range, enforces per-turn caps and cooldowns, keeps counters
-  counters monotonic and milestones sticky, then strips the machine-readable block out of the
+  monotonic and milestones sticky, then strips the machine-readable block out of the prose
-  prose (`backend/app/worldstate/engine.py`). Word-labelled bands (`40–60: minor damage`) are
+  (`backend/app/worldstate/engine.py`). Word-labeled bands (`40–60: minor damage`) make the
-  what make the model reliable at it. No dice, no scripting required.
+  model reliable at it. No dice and no scripting are required.
-- **AI Dungeon-compatible context engine** — memory, author's note, and story cards (world
+- **AI Dungeon-compatible context engine.** Memory, author's note, and story cards (world
-  info) triggered by keywords in recent story text, assembled under a token budget
+  info) are triggered by keywords in recent story text, then assembled under a token budget
   (`backend/app/context/builder.py`).
-- **Insights: total prompt transparency** — every turn stores the exact prompt sent to the
+- **Insights: total prompt transparency.** Every turn stores the exact prompt sent to the
-  model; open 🔍 on any AI action to see each context component, its token cost, and why it was
+  model. Open 🔍 on any AI action to see each context component, its token cost, and why it was
   included.
-- **JavaScript scripting, AI Dungeon-compatible** — `onInput` / `onModelContext` / `onOutput`
+- **JavaScript scripting, AI Dungeon-compatible.** `onInput` / `onModelContext` / `onOutput`
-  modifiers with shared `state` and a `worldEntries` API, executed in an embedded quickjs
+  modifiers share `state` and a `worldEntries` API, and run in an embedded quickjs sandbox
-  sandbox (`backend/app/scripting/`). Real AI Dungeon scripts import and run. In-app
+  (`backend/app/scripting/`). Real AI Dungeon scripts import and run as is. An in-app CodeMirror
-  CodeMirror editor included.
+  editor is included.
-- **Auto-summarization + Memory Bank** — the modern AI Dungeon memory system: AI-generated
+- **Auto-summarization and Memory Bank.** The modern AI Dungeon memory system: AI-generated
   memories every few actions, a running story summary, and embedding-based retrieval that
   pulls old-but-relevant facts back into context, with similarity scores visible in Insights
   (`backend/app/memorybank.py`).
-- **Undo and retry that actually rewind** — undo and retry roll back the world state and script
+- **Undo and retry that actually roll back state.** Undo and retry roll back the world state
-  state to a per-node snapshot, not just the text, and prune the memories that covered the
+  and script state to a per-node snapshot, not just the text, and prune the memories that
-  removed turns. Nothing a retry replaces is thrown away: the old attempt stays as another take
+  covered the removed turns. Nothing a retry replaces is discarded: the old attempt stays as
-  of that turn, and is one keystroke and one click from being a branch of its own.
+  another take of that turn, one keystroke and one click from becoming a branch of its own.
-- **Import/export** — AI Dungeon-compatible formats for scripts and scenarios; JSON for
+- **Import and export.** AI Dungeon-compatible formats for scripts and scenarios; JSON for
-  everything. An adventure exports as `ai-dnd-adventure-v2`, which carries the whole tree —
+  everything else. An adventure exports as `ai-dnd-adventure-v2`, which carries the whole tree:
-  every branch, every take, and the fork points, because those were chosen rather than computed.
+  every branch, every take, and the fork points, since those were chosen rather than computed.
   Files saved in the old single-line format still import.
-- **Optional accounts for hosted deployments** — by default the app is single-user with zero
+- **Optional accounts for hosted deployments.** By default the app is single-user with zero
-  auth friction; set `AIDND_MULTI_USER=1` and visitors play instantly as guests (signed
+  auth friction. Set `AIDND_MULTI_USER=1` and visitors play instantly as guests (signed
-  session cookie), can register (email + password) at any point to keep their data, and each
+  session cookie), can register (email and password) at any point to keep their data, and each
   user gets isolated data plus their own encrypted-at-rest API key. A server-funded **shared
   demo key** with a daily turn cap lets people try it without bringing a key
   (`backend/app/auth.py`).
@@ -82,11 +83,11 @@ live one is what starts a new branch.*
 | | |
 |---|---|
 | ![Insights panel](docs/images/insights.jpg) | ![Scenario editor](docs/images/scenario-editor-npcs.jpg) |
-| **Insights** — the exact prompt for the next turn, broken into components with token counts and the trigger word that pulled each story card in. | **Authoring** — stats with ranges, per-turn caps, cooldowns and word-labelled bands; NPCs the AI addresses by id. |
+| **Insights**: the exact prompt for the next turn, broken into components with token counts and the trigger word that pulled each story card in. | **Authoring**: stats with ranges, per-turn caps, cooldowns, and word-labeled bands; NPCs the AI addresses by id. |
 | ![Script editor](docs/images/script-editor.jpg) | ![Home](docs/images/home.jpg) |
-| **Scripting** — the three AI Dungeon hooks with shared persistent `state`, run in a quickjs sandbox. | **Home** — continue a story in progress or start from a scenario. |
+| **Scripting**: the three AI Dungeon hooks with shared persistent `state`, run in a quickjs sandbox. | **Home**: continue a story in progress or start from a scenario. |
 | ![The branch map](docs/images/branch-map.jpg) | ![The branches panel](docs/images/branches-panel.jpg) |
-| **The tree** — one lane per line, from the moment it left its parent to the moment it ends. The horizontal axis is the story's own clock, so a short branch reads as short. | **Branches** — every line the story has taken, and the three things you can do to one. A line the one you're reading was forked from can't be deleted, and says so. |
+| **The tree**: one lane per line, from the moment it left its parent to the moment it ends. The horizontal axis is the story's own clock, so a short branch reads as short. | **Branches**: every line the story has taken, and the three things you can do to one. A line the one you're reading was forked from can't be deleted, and says so. |
 
 ## Quick start
 
@@ -127,8 +128,8 @@ Open **Settings** in the app and point it at any OpenAI-compatible endpoint:
 | OpenRouter | `https://openrouter.ai/api/v1` | `:free` models cost nothing (no embeddings on the free tier) |
 | OpenAI / Groq / vLLM / … | provider's `/v1` URL | anything speaking `/v1/chat/completions` |
 
-Model name, API key, generation parameters, and (optionally) summary/embedding models for the
+Model name, API key, generation parameters, and (optionally) summary and embedding models for
-Memory Bank are all configured there too — no config files, no rebuild.
+the Memory Bank are all configured there too. No config files and no rebuild are needed.
 
 ## How a turn works
 
@@ -168,14 +169,14 @@ frontend/   React + Vite SPA  ──HTTP/SSE──►  backend/  FastAPI
                                               └─ data.db       SQLite (path overridable via AIDND_DB_PATH)
 ```
 
-In production the backend serves the built SPA from one port (see `Dockerfile`); in
+In production the backend serves the built SPA from one port (see `Dockerfile`). In
-development Vite proxies `/api` to FastAPI.
+development, Vite proxies `/api` to FastAPI.
 
 ## Tests
 
-497 backend tests — unit plus full HTTP integration through the real quickjs scripting engine,
+497 backend tests: unit tests plus full HTTP integration through the real quickjs scripting
-with the LLM provider mocked. CI runs them on every push, alongside the frontend lint/build and
+engine, with the LLM provider mocked. CI runs them on every push, alongside the frontend
-a Docker image build.
+lint/build and a Docker image build.
 
 ```sh
 cd backend && pip install -r requirements.txt -r requirements-dev.txt
@@ -184,71 +185,73 @@ python -m pytest tests/
 
 ## Notes on performance
 
-Two of the tests exist because of bugs that were measured rather than guessed at, and they're
+Two of the tests exist because of bugs that were measured rather than guessed at. They are the
-the most interesting engineering in the repo:
+most interesting engineering in the repo.
 
-- **Database egress, cut ~189x.** Every adventure load was pulling `Action.context_snapshot` —
+- **Database egress, cut about 189x.** Every adventure load pulled `Action.context_snapshot`,
-  the entire assembled prompt, ~74 KB per turn — to read two small fields off it. Moving those
+  the entire assembled prompt at about 74 KB per turn, to read two small fields off it. Moving
-  fields into their own columns and marking the heavy ones `deferred` took one adventure load
+  those fields into their own columns and marking the heavy ones `deferred` took one adventure
-  from 38.5 MB to 0.20 MB. The backfill runs server-side with dialect-specific SQL so the old
+  load from 38.5 MB to 0.20 MB. The backfill runs server-side with dialect-specific SQL, so the
-  data never crosses the wire. `tests/test_egress.py` hooks into SQLAlchemy's cursor events and
+  old data never crosses the wire. `tests/test_egress.py` hooks into SQLAlchemy's cursor events
-  fails if a bulk load ever names those columns again.
+  and fails if a bulk load ever names those columns again.
-- **Turn cost, made flat.** Assembling a turn walked the whole story, so it was O(story length)
+- **Turn cost, made flat.** Assembling a turn walked the whole story, so cost scaled with story
-  — 839 KB of reads at turn 200. `backend/app/context/history.py` now serves tails and slices
+  length: 839 KB of reads at turn 200. `backend/app/context/history.py` now serves tails and
-  from SQL and measures what it fetched; the same turn costs 129 KB and stops growing at around
+  slices from SQL and measures what it fetched. The same turn now costs 129 KB and stops
-  turn 50.
+  growing at around turn 50.
-- **Branching that doesn't cost anything to read.** A branch stores no turns — it stores where it
+- **Branching that costs nothing to read.** A branch stores no turns. It stores where it left
-  left its parent, and borrows everything above that. A 40-turn story forked twenty times loads in
+  its parent, and borrows everything above that. A 40-turn story forked twenty times loads in
-  31,652 B against 31,433 B for the same story flat: **1.007×**, or about 103 B per branch. Reads
+  31,652 bytes against 31,433 bytes for the same story flat: a 1.007x ratio, or about 103 bytes
-  stay cheap because the lineage is windowed like the history is, so the number of SQL clauses is
+  per branch. Reads stay cheap because the lineage is windowed the same way the history is, so
-  bounded by the context window rather than by the number of forks.
+  the number of SQL clauses is bounded by the context window rather than by the number of
+  forks.
 
 ## Visit analytics
 
-The hosted demo keeps its own analytics: an owner-only dashboard at `/analytics` showing
+The hosted demo keeps its own analytics: an owner-only dashboard at `/analytics` shows
 traffic, which shared scenarios get played, turns and demo-key spend, errors, and a funnel
 from *visited* to *played a turn* to *signed up*. It is visible only to the emails listed in
-`AIDND_ANALYTICS_EMAILS`, and the route 404s for everyone else.
+`AIDND_ANALYTICS_EMAILS`, and the route returns 404 for everyone else.
 
-Built into the app rather than bolted on with a third-party script, for reasons specific to
+This is built into the app rather than added with a third-party script, for reasons specific
-this one: the CSP allows `script-src 'self'`, adblockers eat the popular trackers, and none
+to this project: the CSP allows only `script-src 'self'`, ad blockers block the popular
-of them can see the measurement that actually matters here — a turn. Counts are aggregated
+trackers, and none of those trackers can see the measurement that matters here, a turn. Counts
-in memory and flushed as UPSERTs, so a visit is a write and never a read, and every dashboard
+are aggregated in memory and flushed as UPSERTs, so a visit is a write and never a read, and
-query is a `GROUP BY` returning tens of rows however much traffic sits behind it. That last
+every dashboard query is a `GROUP BY` that returns tens of rows regardless of traffic volume.
-part is not incidental; see the egress note above for what reading rows per request costs on
+That matters: see the egress note above for what reading rows per request costs on this stack.
-this stack.
 
 ## Deploy (Render)
 
-The repo ships a [`render.yaml`](render.yaml) blueprint: one Docker web service that
+The repo ships a [`render.yaml`](render.yaml) blueprint: one Docker web service that serves
-serves the SPA and API same-origin, backed by external [Neon](https://neon.tech) Postgres
+the SPA and API same-origin, backed by external [Neon](https://neon.tech) Postgres. The free
-(the free tier has no persistent disk, so the database lives off-box).
+Render tier has no persistent disk, so the database lives off-box.
 
 1. Create a **Neon** project and copy its pooled connection string.
-2. In Render: **New → Blueprint**, point it at this repo. Render reads `render.yaml`.
+2. In Render, choose **New → Blueprint** and point it at this repo. Render reads
-3. Fill the secrets it prompts for (`sync: false` vars): `AIDND_DATABASE_URL` (the Neon
+   `render.yaml`.
-   string); to offer a no-signup demo, `AIDND_DEMO_API_KEY` / `AIDND_DEMO_MODELS`; and to
+3. Fill in the secrets it prompts for (`sync: false` vars): `AIDND_DATABASE_URL` (the Neon
-   see the Visitors dashboard, `AIDND_ANALYTICS_EMAILS` (your own account's email).
+   string); `AIDND_DEMO_API_KEY` and `AIDND_DEMO_MODELS` to offer a no-signup demo; and
-   `AIDND_SECRET_KEY` is generated automatically and kept stable across deploys.
+   `AIDND_ANALYTICS_EMAILS` (your own account's email) to see the Visitors dashboard.
-4. Deploy. Pushes to `main` auto-deploy thereafter. Health check: `/api/health`.
+   `AIDND_SECRET_KEY` is generated automatically and stays stable across deploys.
+4. Deploy. Pushes to `main` auto-deploy after this. The health check is `/api/health`.
 
-On the free tier the service sleeps after ~15 min idle; the first request then takes
+On the free tier the service sleeps after about 15 minutes idle, and the first request after
-~30–60s to wake. Point any keep-warm pinger at `/api/health`, which deliberately doesn't
+that takes about 30 to 60 seconds to wake it. Point any keep-warm pinger at `/api/health`,
-touch the database — waking the database around the clock costs far more than the cold start
+which deliberately doesn't touch the database: waking the database around the clock costs far
-is worth.
+more than the cold start saves.
 
 ## Repo notes
 
-- `plan/` — the phased implementation plan this was built from, kept as a build log. All fourteen
+- `plan/` holds the phased implementation plan this project was built from, kept as a build
-  phases are complete; the later files (11, 12, 14) double as design notes for the state-revert,
+  log. All fourteen phases are complete. The later files (11, 12, 14) also serve as design
-  world-state and story-tree work. [`plan/STATUS.md`](plan/STATUS.md) is the running thread —
+  notes for the state-revert, world-state, and story-tree work.
-  what shipped, what was measured, and what is owed next.
+  [`plan/STATUS.md`](plan/STATUS.md) is the running thread: what shipped, what was measured,
-- [`docs/GUIDE.md`](docs/GUIDE.md) — design notes: how each subsystem works and why it was built
+  and what is owed next.
-  that way, with the measurements behind the decisions. Also rendered as a
+- [`docs/GUIDE.md`](docs/GUIDE.md) holds design notes: how each subsystem works and why it was
+  built that way, with the measurements behind the decisions. It is also rendered as a
   [reading page](https://parththakkar106.github.io/AI-DnD/guide.html).
-- `backend/.env.example` — the few environment variables the backend reads.
+- `backend/.env.example` lists the few environment variables the backend reads.
-- [`docs/self-review.md`](docs/self-review.md) — a full-codebase self-review pass and what came
+- [`docs/self-review.md`](docs/self-review.md) records a full-codebase self-review pass and
-  out of it. All correctness findings are resolved.
+  what came out of it. All correctness findings are resolved.
 
 ## License
 

docs/GUIDE.md

@@ -108,19 +108,19 @@ player input
 Two design choices are visible in that list before any of the details.
 
 **The prompt is snapshotted, not reconstructed.** Every AI action stores the exact text
-that was sent to the model. That's what powers the Insights panel — open any turn and see
+that was sent to the model. That's what powers the Insights panel: open any turn and see
 each context component, its token cost, and why it was included. It's also what makes
 prompt bugs findable. The cost is storage (~74 KB per turn), which turns into a real
-performance problem later — see [2.5](#25-the-189x-egress-fix).
+performance problem later. See [2.5](#25-the-189x-egress-fix).
 
 **Every node records the state it leaves behind.** `state_after` and `world_state_after`
-are stapled onto the action once its hooks and its delta have run, so a node carries the
+are attached to the action once its hooks and its delta have run, so a node carries the
-scoreboard and the RPG stats as they stood when that turn finished. Rewinding to *before*
+stats and the RPG values as they stood when that turn finished. Rewinding to *before*
-a turn is then a read of the node in front of it, which is the same move as switching to
+a turn is then a read of the node in front of it, which is the same operation as switching
-another branch — one mechanism, and it is the whole reason undo, retry and branch
+to another branch: one mechanism, and the reason undo, retry, and branch switching all put
-switching all put the numbers back rather than only rewriting text. (These were `*_before`
+the numbers back instead of only rewriting text. (These were `*_before` fields originally; a
-pictures originally; a tree wants the *after*, because a branch's tip is what a reader
+tree needs the *after* value, because a branch's tip is what a reader standing on it should
-standing on it should see.)
+see.)
 
 ---
 
@@ -138,7 +138,7 @@ whether the story stays coherent.
 
 Send the last N turns. That breaks in two directions: N turns of short exchanges wastes the
 window, and N turns of long ones overflows it. It also throws away the things that matter
-most — the premise, the character sheet, the fact that you promised the innkeeper you'd
+most: the premise, the character sheet, the fact that you promised the innkeeper you'd
 return.
 
 ### What this app does
@@ -149,12 +149,12 @@ Fixed (always included, whatever they cost):
 
 | Section | What it is |
 |---|---|
-| `narrator` | The system prompt — how to write. |
+| `narrator` | The system prompt: how to write. |
 | `world_state_guide` | The stat legend: what each stat means, its range, its bands. |
 | `world_state` | Current values of every stat, plus NPCs in scene. |
 | `world_state_rule` | How to report changes. |
 | `ai_instructions` | Per-adventure steering. |
-| `plot_essentials` | AI Dungeon's "Memory" — the premise. |
+| `plot_essentials` | AI Dungeon's "Memory": the premise. |
 | `story_summary` | The auto-maintained running summary. |
 | `used_memories` | Top-K retrievals from the memory bank. |
 
@@ -184,7 +184,7 @@ of "the model has no idea what just happened". Cards that don't fit are still *r
 to Insights with `included: false`, so the UI can show the lore that got squeezed out.
 
 **History fills newest-first and stops.** Oldest turns fall out. This is the right
-direction because the old material is not actually lost — it has been summarized into
+direction because the old material is not actually lost: it has been summarized into
 memories and the running summary, which are in the fixed section.
 
 **If even the single newest turn is over budget, it gets hard-truncated** rather than
@@ -193,8 +193,8 @@ of the last turn produces something.
 
 **The author's note is injected 3 actions from the end**, not at the top.
 `AUTHORS_NOTE_DEPTH = 3`. Instructions placed near the end of a prompt have more influence
-on what comes next than instructions at the top — recency. The author's note is a steering
+on what comes next than instructions at the top, because of recency. The author's note is a
-control ("keep it tense"), so it goes where steering works.
+steering control ("keep it tense"), so it goes where steering works.
 
 **The world-state reminder goes dead last.** The full emit rule lives up in the system
 block, hundreds of tokens away from where the model starts writing. A one-line reminder
@@ -203,15 +203,15 @@ forgotten.
 
 **Past AI turns get their state block re-attached.** The state block is stripped from the
 text before it's stored, so a replayed history would show the model twenty of its own past
-turns that *contain no state block* — which teaches it, by imitation, to stop emitting one.
+turns that *contain no state block*. That teaches it, by imitation, to stop emitting one.
 So `_history_text()` reconstructs the block from the stored delta and re-appends it when
 building history. The model sees its own pattern and keeps following it.
 
 ### The performance trap hiding in this
 
 Building the context needs the newest ~6,000 tokens of story. The obvious implementation
-reads `adventure.actions` — which loads every row of the adventure — and then throws 90%
+reads `adventure.actions`, which loads every row of the adventure, and then throws 90% of
-of it away. At turn 200 that was 839 KB of database reads to use maybe 70 KB, and it grew
+it away. At turn 200 that was 839 KB of database reads to use maybe 70 KB, and it grew
 every single turn.
 
 `backend/app/context/history.py` fixes it by serving three shapes directly from SQL: a
@@ -225,13 +225,13 @@ projected = int(budget / average * 1.15) + 8
 ```
 
 Each round fetches only what it doesn't already hold, so no row is read twice. Result: the
-same turn costs 129 KB instead of 839 KB, and stops growing at around turn 50 — the cost
+same turn costs 129 KB instead of 839 KB, and stops growing at around turn 50. The cost is
-is bounded by the context budget instead of by the length of the story.
+bounded by the context budget instead of by the length of the story.
 
 There's a second rule in that module worth naming: **if the actions are already loaded in
 memory, slice them instead of querying.** The scripting pipeline hands the whole history to
-user scripts (AI Dungeon's API requires it), so on a scripted adventure the rows are
+user scripts (AI Dungeon's API requires it), so on a scripted adventure the rows are already
-already there — issuing a query beside them would mean paying twice.
+there. Issuing a query beside them would mean paying twice.
 
 ---
 
@@ -241,19 +241,19 @@ Source: `backend/app/worldstate/engine.py`, `plan/12-phase-rpg-world-state.md`.
 
 ### The problem
 
-You want an RPG layer — hit points, trust, quest progress. Who owns the numbers?
+You want an RPG layer: hit points, trust, quest progress. Who owns the numbers?
 
 ### Three options, and why two lose
 
 **Option A: a deterministic dice engine.** The player types "attack the goblin", the
 engine rolls, applies damage, and the model narrates the result. This is what a real RPG
-does. It loses here because the action space is unbounded — the player can type anything,
+does. It loses here because the action space is unbounded: the player can type anything, and
-and mapping arbitrary natural language onto a fixed rules system is a harder problem than
+mapping arbitrary natural language onto a fixed rules system is a harder problem than the
-the one being solved.
+one being solved.
 
 **Option B: the model owns the numbers.** Let it track hp in the prose and trust it. This
 fails immediately. Models are bad at arithmetic, worse at remembering a number across
-twenty turns, and completely unable to obey their own frequency rules — tell one "only
+twenty turns, and completely unable to obey their own frequency rules. Tell one "only
 change this every 5 turns" and it will change it every turn.
 
 **Option C, chosen: the model proposes, the engine disposes.** The model narrates and
@@ -279,10 +279,10 @@ The engine then applies, in order:
 | `max_delta_per_turn` | Losing 90 hp to a stubbed toe |
 | Clamp to `min`/`max` | Negative hp, trust above 100 |
 | Milestones are sticky, `true` only | Un-completing a quest |
-| Flags are two-way booleans | (Deliberately unrestricted — that's what flags are for) |
+| Flags are two-way booleans | (Deliberately unrestricted: that's what flags are for) |
 
-Everything it rejects is *reported*, not silently swallowed — the Insights panel shows
+Everything it rejects is *reported*, not silently swallowed. The Insights panel shows
-applied, clamped and rejected paths per turn, and the chip under each narration shows what
+applied, clamped, and rejected paths per turn, and the chip under each narration shows what
 actually changed.
 
 ### The reliability mechanism: word bands
@@ -295,33 +295,33 @@ A stat can carry **bands**:
                   [60,90,"healthy"],[90,100,"full health"]] }
 ```
 
-Two things use them. The live state block shows the current band label — `hp 55/100 (minor
+Two things use them. The live state block shows the current band label, `hp 55/100 (minor
-damage)` — so the model reads a *word*, not just a number. And the stat guide shows the
+damage)`, so the model reads a *word*, not just a number. And the stat guide shows the
 whole ladder once per turn, so the model can see the full scale it's reasoning across.
 
 The point: models reason well over semantics and badly over arithmetic. "He's badly hurt,
-so a solid hit should take him to very weak" is a judgement a model can make. "55 minus 22
+so a solid hit should take him to very weak" is a judgment a model can make. "55 minus 22 is
-is 33" is one it will get wrong often enough to matter.
+33" is one it will get wrong often enough to matter.
 
 ### The failure philosophy
 
 Nothing in the world-state engine raises. A malformed delta returns `{}` and the turn
-continues. The parser is deliberately tolerant — it strips trailing commas and leading `+`
+continues. The parser is deliberately tolerant: it strips trailing commas and leading `+`
 signs on numbers, both of which weaker free models emit and strict JSON rejects. It accepts
-a fence labelled `state`, one labelled `json`, or an unlabelled one, and falls back to a
+a fence labeled `state`, one labeled `json`, or an unlabeled one, and falls back to a bare
-bare JSON object hugging the end of the text — but only if it parses into something that
+JSON object at the end of the text, but only if it parses into something that looks like a
-looks like a delta, so prose ending in `}` is never eaten.
+delta, so prose ending in `}` is never eaten.
 
 This matters because the hosted demo runs on free-tier models. A stricter parser would mean
 a good model works and a free one doesn't.
 
 ### One call, not two
 
-The model narrates *and* emits the delta in a single request. The alternative — narrate,
+The model narrates *and* emits the delta in a single request. The alternative, narrating and
-then a second call to extract structured state — is more reliable per call and costs twice
+then making a second call to extract structured state, is more reliable per call and costs
-the latency and twice the rate-limit budget. On the free tier (20 requests/minute) that
+twice the latency and twice the rate-limit budget. On the free tier (20 requests/minute)
-would halve the playable turn rate. The tolerant parser plus the terminal reminder was the
+that would halve the playable turn rate. The tolerant parser plus the terminal reminder was
-cheaper way to buy the same reliability.
+the cheaper way to buy the same reliability.
 
 ---
 
@@ -339,9 +339,9 @@ Tell the model its budget: *"keep this turn under about N words"*.
 
 ### What the measurement showed
 
-Average turn length went from **174 words to 246** — every run longer than every unhinted
+Average turn length went from **174 words to 246**, and every run was longer than every
-run (n=5). Phrased as a budget, the number reads as a *target to fill*. The hint pushed
+unhinted run (n=5). Phrased as a budget, the number reads as a *target to fill*. The hint
-turns toward the very wall it existed to protect.
+pushed turns toward the very wall it existed to protect.
 
 ### The fix
 
@@ -361,12 +361,12 @@ Average came back to 170 words, and the state block survived at tight caps.
 words = int((max_output_tokens - 50) * 0.75 * 0.90)
 ```
 
-- `- 50` (`LENGTH_HEADROOM`) — tokens held back for the state block itself.
+- `- 50` (`LENGTH_HEADROOM`): tokens held back for the state block itself.
-- `* 0.75` (`WORDS_PER_TOKEN`) — models can't count their own tokens, but they do follow a
+- `* 0.75` (`WORDS_PER_TOKEN`): models can't count their own tokens, but they do follow a
   word budget. English prose is roughly 0.75 words per token.
-- `* 0.90` (`LENGTH_BUFFER`) — a word budget is a suggestion the model overshoots; the cap
+- `* 0.90` (`LENGTH_BUFFER`): a word budget is a suggestion the model overshoots, and the cap
   it protects is a hard wall. Aim 10% short so the overshoot lands in slack.
-- Below 40 words the hint is dropped entirely — it stops earning its tokens.
+- Below 40 words the hint is dropped entirely: it stops earning its tokens.
 
 ---
 
@@ -377,7 +377,7 @@ Source: `backend/app/memorybank.py`.
 ### The problem
 
 Story history falls out of the context window as the adventure grows. Turn 4 said you
-promised the innkeeper you'd return. At turn 90 that's long gone from the prompt — but if
+promised the innkeeper you'd return. At turn 90 that's long gone from the prompt, but if
 you walk back into the inn, it should come back.
 
 ### The three layers
@@ -401,23 +401,23 @@ back into the prompt.
 
 ### The decisions inside it
 
-**A memory hangs off the node whose block it ends on.** Not off the adventure, and not off
+**A memory attaches to the node whose block it ends on.** Not to the adventure, and not to
-a *position* in a list of actions — off a `(branch_id, depth)` coordinate. That is what
+a *position* in a list of actions, but to a `(branch_id, depth)` coordinate. That is what
 makes "which memories described this turn?" an indexed lookup rather than a scan for rows
 whose covered range has fallen off the end of the story, and it is what makes memories
 inherit correctly across a fork: the ones above the fork point already sit on ancestors
 both lines read.
 
-It is also the repair. When a turn's text is replaced or removed — a retry, an undo, a
+This is also how repair works. When a turn's text is replaced or removed (a retry, an undo,
-deleted action — `forget_node` withdraws the memory hanging off that coordinate *and*
+a deleted action), `forget_node` withdraws the memory attached to that coordinate and
 rewinds both marks to just before the stretch it covered, so the ground is summarized again
 from what the story now says. An earlier version instead held the newest action back a turn
-so it could never be summarized before it stopped being retryable; that is no longer needed,
+so it could never be summarized before it stopped being retryable. That is no longer
-because the repair exists whether or not the invalidation happens at the tip.
+needed, because the repair exists whether or not the invalidation happens at the tip.
 
 **Cursors only advance on success.** Every AI call in this module is best-effort. If
 summarization fails, the function returns and the cursor is unchanged, so the same block is
-retried on a later turn. There is no retry loop, no dead-letter queue, no backoff — the
+retried on a later turn. There is no retry loop, no dead-letter queue, and no backoff: the
 cadence *is* the retry mechanism. Failures are logged to the debug page.
 
 **Summarization is fire-and-forget, in a background task with its own DB session.** The
@@ -437,7 +437,7 @@ truncate and score garbage silently. An explicit length check returns 0.0 instea
 
 **Eviction is LRU-ish, and evicted memories are kept.** Over capacity (default 200), the
 least-used, least-recently-used unpinned memories are marked `forgotten` rather than
-deleted — so the UI can still show them and you can un-forget one.
+deleted, so the UI can still show them and you can un-forget one.
 
 **Background calls never spend the shared demo key.** The summarization and embedding
 providers are built directly from the user's own settings and never from the demo config,
@@ -454,7 +454,7 @@ anything makes a 20-second generation feel broken.
 
 **Server-Sent Events (SSE)** is the mechanism: an HTTP response that stays open and pushes
 `data: {...}` lines as they become available. It's one-directional (server → browser),
-which is exactly what's needed here — WebSockets would be a bidirectional connection for a
+which is exactly what's needed here. WebSockets would be a bidirectional connection for a
 unidirectional problem.
 
 The chain:
@@ -473,7 +473,7 @@ text), `stopped` (a script blocked the turn), `error`, `done`.
 
 Two production details that only show up when hosted:
 
-- `X-Accel-Buffering: no` — nginx-style reverse proxies buffer responses by default, which
+- `X-Accel-Buffering: no`: nginx-style reverse proxies buffer responses by default, which
   turns a stream into one big delivery at the end. This header tells them to flush each
   event.
 - The security-headers and body-size middlewares are written as **pure ASGI** rather than
@@ -481,7 +481,7 @@ Two production details that only show up when hosted:
   break streaming.
 
 **The empty-reply case is diagnosed, not reported as "empty".** If a reasoning model
-streams thinking but no story text, it spent its whole budget thinking — the error says so
+streams thinking but no story text, it spent its whole budget thinking. The error says so
 and tells you which three settings to change.
 
 ---
@@ -498,18 +498,18 @@ The safety properties are mostly structural:
 
 | Property | How |
 |---|---|
-| No filesystem, network, or process access | QuickJS has none by default — nothing was removed, nothing was added |
+| No filesystem, network, or process access | QuickJS has none by default: nothing was removed, nothing was added |
 | Memory cap | 16 MB per run |
 | CPU cap | 2 seconds per run |
 | No shared state between runs | A fresh `Context` per hook execution |
 | A broken script can't break a turn | Every failure comes back as `.error` with text/state/cards unchanged; the pipeline logs it and continues |
 
-Data crosses the boundary as JSON — Python serializes `{state, text, history, storyCards,
+Data crosses the boundary as JSON: Python serializes `{state, text, history, storyCards,
 info}` in, and the script's results out. There is no object bridge to exploit.
 
 One deliberate bug-compatibility: `addStoryCard` returns the new card's *index*, so the
 first card returns `0`, which is falsy, so `if (!addStoryCard(...))` misfires. That's
-upstream AI Dungeon's behaviour. It's documented in the code and left alone, because
+upstream AI Dungeon's behavior. It's documented in the code and left alone, because
 matching real scripts is the whole point of the feature.
 
 ---
@@ -517,7 +517,7 @@ matching real scripts is the whole point of the feature.
 ## 1.8 Why there is no agent framework
 
 Graph-based agent frameworks (LangGraph and similar) earn their complexity with
-**branching, cyclic, multi-step control flow** — a graph of nodes where the path depends on
+**branching, cyclic, multi-step control flow**: a graph of nodes where the path depends on
 what the model decides, with loops, retries, tool calls, and persisted state between steps.
 
 This turn pipeline is a **fixed linear sequence with exactly one model call**. There is no
@@ -533,13 +533,13 @@ abstraction, its serialization model, and its debugging surface to express a str
 There is also a specific reason a framework's context handling wouldn't fit: **the
 budgeting logic is the product.** Buffer-window and summary-memory abstractions are
 opinionated about how to fit history into a window. Here the Insights panel exposes each
-context component, its token cost, and the trigger word that pulled it in — which means the
+context component, its token cost, and the trigger word that pulled it in, so the assembly
-assembly has to be explicit and inspectable.
+has to be explicit and inspectable.
 
-**When it would be the right call:** if the design went toward the two-call version —
+**When it would be the right call:** if the design went toward the two-call version, where
-narrate, then a separate structured-extraction step, with a retry branch when extraction
+narration is followed by a separate structured-extraction step, with a retry branch when
-fails and a tool-calling path for dice — that is a graph, and hand-rolling it would get
+extraction fails and a tool-calling path for dice, that is a graph, and hand-rolling it
-ugly fast.
+would get ugly fast.
 
 ---
 
@@ -576,8 +576,8 @@ behind it.
 ### The problem
 
 The story used to be a list, and a mutable one. Retry rewrote the last entry in place;
-undo and delete removed entries from the middle. Everything derived from the story —
+undo and delete removed entries from the middle. Everything derived from the story, such as
-the memories, the running summary, the two marks saying how far each had got — was
+the memories, the running summary, and the two marks saying how far each had got, was
 indexed by *position in that list*, and a position means something different after
 anything in front of it is deleted.
 
@@ -603,8 +603,8 @@ Make the story a tree, and none of them are reachable.
 
 Every action is a **node** with a `branch_id` and a `depth`. A **branch** is one line
 through the tree; it holds the nodes played on it and *borrows* everything before its
-fork point from its ancestors. Nothing is ever copied and — apart from an explicit
+fork point from its ancestors. Nothing is ever copied, and apart from an explicit delete,
-delete — nothing is ever removed.
+nothing is ever removed.
 
 ```
 branches(id, adventure_id, parent_branch_id, fork_depth, lineage, name)
@@ -636,38 +636,38 @@ keep the shape they already had.
 ### The lineage, and why fork count doesn't cost anything
 
 The OR-clause above is not reconstructed per read. It is stored on the branch row as
-`lineage` — `[(C, ∞), (B, 5), (A, 3)]` — computed once when the fork happens, from the
+`lineage`, for example `[(C, ∞), (B, 5), (A, 3)]`, computed once when the fork happens,
-parent's lineage plus one entry. `context/lineage.py` is the only module that knows how
+from the parent's lineage plus one entry. `context/lineage.py` is the only module that
-to turn it into a query, which is deliberate: one forgotten clause shows the wrong story
+knows how to turn it into a query, which is deliberate: one forgotten clause shows the
-and reports nothing.
+wrong story and reports nothing.
 
 Two properties of the shape do the real work:
 
 - **The ranges are disjoint and descending.** A branch's own nodes always sit deeper than
   its fork point, and each ancestor is capped at the fork depth of the branch beneath it.
   So ordering the whole clause by `depth DESC` reads entry 0's nodes, then entry 1's,
-  then entry 2's — which means a tail read can use the newest few entries and stop.
+  then entry 2's, which means a tail read can use the newest few entries and stop.
 - **Clause count is bounded by the context window, not by fork count.** A 200-fork story
   whose newest branch is 40 turns long reads with *one* clause, because the window is
   covered before the second entry is reached.
 
 A branch stores no story of its own, so a fork costs an id, a parent, a fork depth and a
 cached ancestry. Measured on a 40-turn story forked twenty times against the same story
-flat: a page load of **31,652 B against 31,433 B — 1.007×**, or about **103 bytes per
+flat: a page load of **31,652 B against 31,433 B, a 1.007× ratio**, or about **103 bytes
-branch**. No migration, no vacuum, no copy.
+per branch**. No migration, no vacuum, no copy.
 
 ### What a player actually does
 
 None of the above is what the screen shows. In the player's words:
 
 > Any turn can gain another **take**. On an AI turn that means regenerate; on your own
-> message it means type something else. Stepping between takes with `‹ 2/4 ›` is free —
+> message it means type something else. Stepping between takes with `‹ 2/4 ›` is free:
 > the story below simply empties, because that take has no children yet. **A branch is
 > created when you write below a take that is not the live one**, never before.
 
 That rule collapses two operations into one and deletes a distinction from the UI. The
 first version of this screen had a chip that *switched* at the tip and only *previewed*
-above it, with a second button to take that line — one control whose meaning depended on
+above it, with a second button to take that line: one control whose meaning depended on
 where the reader was standing. The rule above replaced it with a pager that only ever
 steps, a fork button on every turn, and no tip-versus-past distinction at all. The
 distinction survives in the implementation, where it decides whether a write needs a
@@ -678,7 +678,7 @@ switch and no branch is created.
 
 The load-bearing detail, and the one that is not obvious.
 
-The natural way to find "the other takes of this turn" is by coordinate — same branch,
+The natural way to find "the other takes of this turn" is by coordinate: same branch,
 same depth. It is wrong in both directions:
 
 ```
@@ -693,8 +693,8 @@ land on different branches. It gets `C` wrong: once C has been forked onto a bra
 its own it is alone at its coordinate and reads `1/1`, having lost C1 and C2 from a pager
 that must still say `1/3`.
 
-So a node carries `parent_id`, read for nothing but this. The alternative — making a
+So a node carries `parent_id`, read for nothing but this. The alternative, making a
-branch's fork point a *node* rather than a depth, so a promoted take never moves — was
+branch's fork point a *node* rather than a depth so a promoted take never moves, was
 rejected: the whole point of `lineage` is that a read is an OR-clause per branch instead
 of a walk up parent pointers, and re-pointing the fork at a node changes path resolution
 itself, dragging in the cursors, memory depths and both bundle formats. `parent_id` is
@@ -702,7 +702,7 @@ one indexed lookup, never a walk, and nothing about how a path resolves changes.
 
 ### Cursors become anchors
 
-The two marks — how far the memory bank has got, how far the summary has got — used to
+The two marks, how far the memory bank has got and how far the summary has got, used to
 be counts. A count is a position in a list, and every rule about sliding them, rewinding
 them and translating between positions and `Action.index` existed to patch up the fact
 that the list moves.
@@ -720,23 +720,23 @@ existed because a retry could rewrite an action the mark had already passed.
 
 ### Derived work attaches to the node that produced it
 
-Generalise the rule and a lot falls out: *anything derived hangs off the node that
+Generalize the rule and a lot falls out: *anything derived attaches to the node that
-produced it*. A memory covering depths 37–42 hangs off that branch's node 42 and is
+produced it*. A memory covering depths 37–42 attaches to that branch's node 42 and is
 invisible to any path that does not run through it. Shared ancestors are therefore shared
-automatically, so **a fork needs nothing recreated** — the memories above the fork point
+automatically, so **a fork needs nothing recreated**: the memories above the fork point
 are already on the ancestors both lines read.
 
 The subtle case is the memory sitting *at* the forked coordinate. The first cut moved it
 onto the new branch and re-anchored the marks naming it. Both are wrong for the same
 reason: that memory describes whichever attempt was live at that coordinate, which is the
-one staying on the parent. The right answer needs no code — the lineage caps the parent
+one staying on the parent. The right answer needs no code: the lineage caps the parent one
-one depth short of the fork, so the memory is simply out of range from the new branch,
+depth short of the fork, so the memory is simply out of range from the new branch,
 invisible to both the retrieval clause and the anchor read. The new line summarizes that
 ground again, from the text it actually tells.
 
 Hand-written memories obey the same rule. One used to carry a NULL depth, described as
-"belongs to the adventure rather than to a path" — which sounds harmless and is not: a
+"belongs to the adventure rather than to a path". That sounds harmless and is not: a NULL
-NULL is a coordinate no fork can cap, so a note typed on one line followed the reader onto
+is a coordinate no fork can cap, so a note typed on one line followed the reader onto
 branches whose events it never described. They are anchored at the head instead: *the
 story you were reading when you wrote it*.
 
@@ -747,7 +747,7 @@ also why branch management could not be a nice-to-have: without a way to delete
 storage grows without limit.
 
 The delete rule has two halves and the second is easy to miss. Refusing to delete the
-line being read is obvious. The other half is refusing any line it was **forked from** —
+line being read is obvious. The other half is refusing any line it was **forked from**:
 `parent_branch_id` cascades, so deleting an ancestor takes the head with it and leaves
 `head_branch_id` pointing at a row that is gone. One membership test against the head's
 own lineage covers both, because a lineage already names itself and every branch it
@@ -757,7 +757,7 @@ button can say so before it is pressed.
 ### The migration, and what it deliberately did not do
 
 There is no feature flag. **A linear story is a tree with one branch**, so the
-intermediate states were not half-migrated — they were the same product with a superset
+intermediate states were not half-migrated: they were the same product with a superset
 schema underneath, which made "existing adventures are unaffected" a literal, testable
 pass condition at every step. A flag would have bought two live code paths through the
 context builder, the memory bank, undo and retry at once.
@@ -767,8 +767,8 @@ were kept unread for a release rather than dropped with the migration that stopp
 them, so that a redeploy of the previous build is still a way out. Dropping columns is the
 one step that isn't.
 
-One operational note that generalises: on Postgres, a migration that rewrites every row of
+One operational note that generalizes: on Postgres, a migration that rewrites every row of
-`actions` roughly doubles the table and only `VACUUM FULL` gives it back — 79 MB reclaimed
+`actions` roughly doubles the table, and only `VACUUM FULL` gives it back: 79 MB reclaimed
 in 5.5 s on one occasion. But bloat scales with the **heap**, and `context_snapshot` is 94%
 of this table and lives out of line, so a migration touching only small columns reuses the
 existing TOAST pointer and costs a tenth of that. Read the sizes from `sum(octet_length())`
@@ -779,14 +779,14 @@ makes bloat look smaller.
 
 - **The two marks are one pair on the adventure**, not one per branch. Switching branches
   makes the mark on the line being left unreadable from the new one, and that ground is
-  summarized again. It answers "nothing covered", which is the safe direction — redo the
+  summarized again. It answers "nothing covered", which is the safe direction: redo the
-  work, never skip it — but switching back and forth costs AI calls. Per-branch cursors
+  work, never skip it. But switching back and forth costs AI calls. Per-branch cursors
   are the fix if it ever matters.
 - **Story cards stay adventure-wide.** A card invented on branch B shows on branch A.
   Event-sourcing card changes onto nodes was considered and rejected.
 - **Editing an already-summarized action still leaves its memory stale.** The machinery to
-  fix it now exists — an edit could write a sibling take and switch to it, which is a retry
+  fix it now exists: an edit could write a sibling take and switch to it, which is a retry
-  the player typed — but it does not do that yet.
+  the player typed. It does not do that yet.
 
 ## 2.3 Undo and retry that actually rewind
 
@@ -794,17 +794,17 @@ Most implementations of undo delete the last message. That's wrong here, because
 mutates three things: the text, the scripting scoreboard (`script_state`), and the RPG
 stats (`world_state`).
 
-**The mechanism:** every node carries `state_after` and `world_state_after` — deep copies
+**The mechanism:** every node carries `state_after` and `world_state_after`, deep copies
 of what the adventure looked like once that turn had played. Rewinding to before a turn is
 a read of the node in front of it, so undo, retry and a branch switch are the same
 restore. The cooldown clock comes along for free: it lives inside the world state, in
 `_meta.last_changed`, so each line of the story carries its own without anything having to
 know there is one.
 
-**Nothing a retry replaces is thrown away.** The old attempt stays as another **take** of
+**Nothing a retry replaces is discarded.** The old attempt stays as another **take** of
-that turn — a sibling node at the same coordinate, `live` false — and the pager steps
+that turn, a sibling node at the same coordinate with `live` set to false, and the pager
-between them. Which is to say retry is not a special case: it is the tree, with the branch
+steps between them. Retry is not a special case: it is the tree, with the branch not yet
-not yet created. See [2.2](#22-the-story-is-a-tree).
+created. See [2.2](#22-the-story-is-a-tree).
 
 Three details that are easy to get wrong:
 
@@ -825,9 +825,10 @@ take belonging to a line nobody asked about. Anything that reads a take group an
 *writes* has to say whether it means the turn or the coordinate.
 
 **If the regeneration fails, the rollback is reversed.** `generate_turn` wraps the
-generator in a `try/finally`: if it ends without saving — a provider error, an empty reply,
+generator in a `try/finally`: if it ends without saving, whether from a provider error, an
-a script `stop`, or the browser hanging up — the previous take is put back in charge.
+empty reply, a script `stop`, or the browser hanging up, the previous take is put back in
-Otherwise the state on the server would drift from the text still on the user's screen.
+charge. Otherwise the state on the server would drift from the text still on the user's
+screen.
 
 ## 2.4 The turn lock
 
@@ -854,11 +855,11 @@ async def with_turn_lock(adventure_id, gen):  # wraps the SSE generator
 ```
 
 In-memory, so it's a single-process guarantee. That's honest for the deployment this
-targets — one Render web service. Two processes would need the lock in the database.
+targets: one Render web service. Two processes would need the lock in the database.
 
 ## 2.5 The 189x egress fix
 
-**The setup:** `Action.context_snapshot` holds the entire assembled prompt for a turn —
+**The setup:** `Action.context_snapshot` holds the entire assembled prompt for a turn,
 about 74 KB per row, 94% of the database.
 
 **The bug:** every adventure load pulled that column for every action, to read two small
@@ -869,7 +870,7 @@ report). SQLAlchemy loads all columns by default.
 
 1. Move the two small things that *are* needed for every action into their own column
    (`Action.world_delta`).
-2. Mark the heavy columns `deferred` — `context_snapshot`, `variants`, `reasoning` — so
+2. Mark the heavy columns `deferred` (`context_snapshot`, `variants`, `reasoning`), so
    they're only fetched when explicitly asked for.
 3. Backfill the new column with dialect-specific server-side SQL, so the old data is
    extracted inside the database and never crosses the wire.
@@ -883,7 +884,7 @@ not on a timing.
 
 One more detail from that test's design: the count query is written as a real
 `SELECT count(...)` rather than `query.count()`, because SQLAlchemy's `.count()` wraps the
-entity select in a subquery, so the emitted SQL names every column — including the deferred
+entity select in a subquery, so the emitted SQL names every column, including the deferred
 ones. No bytes come back either way, but the database still has to read them, and a guard
 that greps SQL cannot tell the two apart.
 
@@ -899,7 +900,7 @@ No Alembic. An append-only list of `(version, SQL)` pairs, with the current vers
 in SQLite's `PRAGMA user_version` or a one-row table on Postgres. 64 versions so far.
 
 - A **fresh** database is created by `Base.metadata.create_all()` (always current) and
-  stamped at the latest version — it never replays history.
+  stamped at the latest version; it never replays history.
 - An **existing** database runs every migration above its stored version, in order.
 
 Why this and not Alembic: for a single-file SQLite app that a user might have been running
@@ -909,9 +910,9 @@ environment. This is 250 lines and you can read all of it.
 
 The constraint it creates is written at the top of the file: change `models.py` (so fresh
 databases are current) *and* append a pair here (so existing ones upgrade). Migrations 2–23
-predate Postgres support and use SQLite-only syntax — harmless, because every Postgres
+predate Postgres support and use SQLite-only syntax. This is harmless, because every
-database starts fresh and never replays them, but anything added since must run on both
+Postgres database starts fresh and never replays them, but anything added since must run
-dialects.
+on both dialects.
 
 One migration worth reading (#10, repairing duplicate action indexes) uses `UPDATE … FROM`
 with a window function rather than a correlated subquery, because SQLite may evaluate a
@@ -929,7 +930,7 @@ correlated subquery against partially-updated rows and produce duplicates again
 | | Local (default) | Hosted |
 |---|---|---|
 | Users | One auto-created "local user" | Guest on first visit, optional account |
-| Auth | None — no cookies, no login UI | Signed session cookie |
+| Auth | None: no cookies, no login UI | Signed session cookie |
 | Rate limits | Off | On |
 | Row caps | Off | On |
 | API docs (`/docs`) | On | Off |
@@ -941,13 +942,13 @@ deployment needs all four of those to be the opposite. Rather than two builds, t
 differences are gated at each site.
 
 **Guests upgrade in place.** A visitor gets a guest `User` row on first load. Registering
-sets `email` and `password_hash` on that *same row* — so every adventure they played as a
+sets `email` and `password_hash` on that *same row*, so every adventure they played as a
 guest survives with no re-parenting and no migration step. Three kinds of row share the
 users table: local (email NULL, not guest), guest (email NULL, guest), registered (email
 set).
 
 **Guests expire; accounts don't.** One row per curious visitor adds up, so `cleanup.py`
-deletes guests idle for `AIDND_GUEST_RETENTION_DAYS` (default 5) — measured as
+deletes guests idle for `AIDND_GUEST_RETENTION_DAYS` (default 5), measured as
 `COALESCE(last_seen_at, created_at)`, because `_touch` only writes `last_seen_at` hourly
 and a guest minted by `/auth/me` has NULL until its second request. The filter requires
 both `is_guest` *and* `email IS NULL`, so upgrading in place is also how you opt out of
@@ -957,7 +958,7 @@ every few hours.
 It's a single Core `DELETE`, not `db.delete(user)`: the ORM path would SELECT every
 adventure, action and memory into Python purely to delete them, and the FK graph is
 `ON DELETE CASCADE` from `users` all the way down, so the database can do the whole graph
-in one statement. Nothing a guest owns is visible to anyone else either — `is_public` is
+in one statement. Nothing a guest owns is visible to anyone else either: `is_public` is
 output-only, so shared content is exactly the seeded scenarios, which have `user_id NULL`
 and never match the filter.
 
@@ -969,11 +970,11 @@ is a spending surface, so it's the most defended code in the project.
 `resolve_provider_config()` is the single place the BYOK-vs-demo decision is made, and on
 the demo branch it pins **two** things:
 
-- **The model** — to a whitelist. A caller-supplied override or a hand-edited settings row
+- **The model**, pinned to a whitelist. A caller-supplied override or a hand-edited
-  can't aim a server-funded key at an expensive model. Anything unrecognised falls back to
+  settings row can't aim a server-funded key at an expensive model. Anything unrecognized
-  the first whitelisted model.
+  falls back to the first whitelisted model.
-- **The endpoint** — to the configured demo URL. Otherwise the key could be redirected to a
+- **The endpoint**, pinned to the configured demo URL. Otherwise the key could be
-  URL the user controls and harvested.
+  redirected to a URL the user controls and harvested.
 
 Plus a daily per-user turn cap (default 20), checked *before* the player's input is stored
 so a capped player doesn't get their message saved with no reply, and counted only after a
@@ -982,12 +983,12 @@ successful turn.
 There's a defensive `__post_init__` on the config object that raises if a demo config
 somehow carries a non-whitelisted model. The comment on it records a real bug: the check
 tests `using_demo`, **not** `api_key == DEMO_API_KEY`. Keying on the key value looks
-stricter but is wrong — the demo key is an ordinary OpenRouter key, so a user can
+stricter but is wrong: the demo key is an ordinary OpenRouter key, so a user can
 legitimately paste that same key into their own settings as BYOK, and then every resolution
 raised, 500ing even `GET /auth/me` and taking the whole SPA down. `using_demo` is what
 actually means "the server is paying".
 
-Background work (summarization, embeddings) is excluded from the demo key entirely — those
+Background work (summarization, embeddings) is excluded from the demo key entirely: those
 are unmetered calls, and unmetered calls on a server-funded key is a bill.
 
 ## 3.3 Secrets
@@ -997,11 +998,11 @@ Everything derives from one server-side secret (`AIDND_SECRET_KEY`).
 | Thing | Mechanism |
 |---|---|
 | Passwords | `hashlib.scrypt`, N=2^14, r=8, p=1, per-password salt, constant-time compare. Stdlib, so no extra dependency. |
-| Sessions | `v1.<user_id>.<HMAC-SHA256>`, no expiry — long-lived guest sessions are the point. A cookie can outlive a swept guest row; that resolves to a 401, which the frontend already turns into a fresh session. |
+| Sessions | `v1.<user_id>.<HMAC-SHA256>`, no expiry: long-lived guest sessions are the point. A cookie can outlive a swept guest row; that resolves to a 401, which the frontend already turns into a fresh session. |
-| Stored LLM API keys | Fernet (AES) encryption at rest, key derived from the secret, `enc:` prefix so legacy plaintext rows are recognisable and migratable. |
+| Stored LLM API keys | Fernet (AES) encryption at rest, key derived from the secret, `enc:` prefix so legacy plaintext rows are recognizable and migratable. |
 
 The secret auto-generates into a file next to the database for local installs (zero config),
-but **multi-user mode refuses to start without the env var** — with an error message that
+but **multi-user mode refuses to start without the env var**, with an error message that
 explains why and gives you the command to generate one. Hosted filesystems are ephemeral; a
 regenerated secret on every deploy would silently log out every user and orphan their stored
 API keys.
@@ -1025,11 +1026,11 @@ rather than raising, so the user just re-enters their key instead of hitting a 5
 Rate limits are keyed per user when one is known (accounts survive IP changes) and per IP
 otherwise, in fixed windows held in memory, with a pruning pass so the per-IP dict can't
 grow without bound. Import endpoints check bundle list lengths against the same caps live
-creation enforces — otherwise the cap is trivially bypassed by uploading a file.
+creation enforces, otherwise the cap is trivially bypassed by uploading a file.
 
 Security headers on every response: `nosniff`, `X-Frame-Options: DENY`,
-`Referrer-Policy: same-origin`, and a CSP allowing exactly what the SPA uses — same-origin
+`Referrer-Policy: same-origin`, and a CSP allowing exactly what the SPA uses: same-origin
-everything, inline styles (React needs them), Google Fonts.
+everything, inline styles (React needs them), and Google Fonts.
 
 ## 3.5 Deployment
 
@@ -1053,13 +1054,13 @@ push.
 
 A hosted demo raises a question a local app never does: is anyone using it, and do they get
 anywhere? The answer is an owner-only dashboard at `/analytics`, gated on
-`AIDND_ANALYTICS_EMAILS` — a list kept separate from `AIDND_POWER_USERS`, since an unmetered
+`AIDND_ANALYTICS_EMAILS`, a list kept separate from `AIDND_POWER_USERS`, since an unmetered
 tester is not automatically someone who should see the traffic.
 
 **Why it isn't a third-party script.** The CSP allows `script-src 'self'`, so a tracker would
-mean loosening it; adblockers eat the popular ones, which silently biases exactly the
+mean loosening it. Ad blockers block the popular ones, which silently biases exactly the
-technical audience this project is shown to; and none of them can see the measurement that
+technical audience this project is shown to. And none of them can see the measurement that
-matters here — a *turn*. The interesting funnel step is not a pageview.
+matters here: a *turn*. The interesting funnel step is not a pageview.
 
 **Egress is the budget.** After the 189x fix (§2.5) it would be perverse to add a feature
 that reads rows per request. So counts accumulate in a process-local dict and flush every 60
@@ -1068,23 +1069,23 @@ seconds as UPSERTs: **a visit is a write and never a read**. Storage is a generi
 Every dashboard query is a `GROUP BY` that returns tens of rows regardless of the traffic
 behind it, so a month costs a few kilobytes to read back. The cost of the buffer is that a
 hard restart can lose up to a minute; the flusher also runs on shutdown, and on a tier that
-sleeps when idle the buffer it sleeps on is empty anyway.
+sleeps when idle, the buffer it sleeps on is empty anyway.
 
-**The numbers are the server's, not the browser's.** The client reports one fact — which page
+**The numbers are the server's, not the browser's.** The client reports one fact, which page
-was viewed — and even that is normalized to a route (`/play/12` → `/play/:id`) against a
+was viewed, and even that is normalized to a route (`/play/12` → `/play/:id`) against a
 whitelist, so the page list cannot be polluted by anything a stranger posts. Everything that
-means something — a turn, an adventure, a sign-up — is recorded by the code that performs it.
+means something, such as a turn, an adventure, or a sign-up, is recorded by the code that
-That also fixes a blind spot: a failed turn is an HTTP 200 with a bad ending, so a
+performs it. That also fixes a blind spot: a failed turn is an HTTP 200 with a bad ending, so
-status-code tally cannot see it, and a demo whose model has started refusing looks perfectly
+a status-code tally cannot see it, and a demo whose model has started refusing looks
-healthy from outside. `turn_error` is counted where the SSE error is written.
+perfectly healthy from outside. `turn_error` is counted where the SSE error is written.
 
-The funnel counts **people, not clicks** — a player who starts six adventures is one person
+The funnel counts **people, not clicks**: a player who starts six adventures is one person
-who started an adventure — which is the entire reason the per-visitor-day table exists.
+who started an adventure, which is the entire reason the per-visitor-day table exists.
 
-One smaller decision worth naming: error buckets are labelled by the matched *route template*,
+One smaller decision worth naming: error buckets are labeled by the matched *route
-never the requested path. That gives one bucket per endpoint instead of one per adventure id,
+template*, never the requested path. That gives one bucket per endpoint instead of one per
-and — the reason it isn't merely tidier — an unmatched path is entirely attacker-chosen, so
+adventure id. The reason it isn't merely tidier is that an unmatched path is entirely
-labelling by it would let anyone mint rows.
+attacker-chosen, so labeling by it would let anyone mint rows.
 
 ---
 
@@ -1092,9 +1093,9 @@ labelling by it would let anyone mint rows.
 
 For the parts that are just how the web works, not decisions.
 
-**Frontend and backend are two programs.** In development they're two servers — Vite on
+**Frontend and backend are two programs.** In development they're two servers: Vite on 5173
-5173 serving React, FastAPI on 8000 serving the API — and Vite proxies `/api` to FastAPI so
+serving React, and FastAPI on 8000 serving the API. Vite proxies `/api` to FastAPI so
-the browser thinks it's all one origin (which avoids CORS entirely). In production there's
+the browser thinks it's all one origin, which avoids CORS entirely. In production there's
 one server: FastAPI serves the built React files as static assets from the same port.
 
 **SPA routing.** React Router handles URLs like `/play/3` in the browser without a round
@@ -1105,7 +1106,7 @@ unaffected.
 
 **Sessions.** A cookie is a small value the browser stores and automatically attaches to
 every request to that site. Here it holds `v1.<user_id>.<signature>`. The server doesn't
-store sessions anywhere — it re-verifies the signature on each request, which is why there's
+store sessions anywhere; it re-verifies the signature on each request, which is why there's
 no session table.
 
 **The 401 retry.** If the cookie is missing or stale, any API call returns 401. The frontend
@@ -1136,7 +1137,7 @@ text appears to type itself.
 | Context defaults | author's note at depth 3, cards capped at 40% of elastic budget |
 | Memory cadence | memory / 6 turns, summary / 15 turns, top-5 retrieval |
 
-Two of the tests encode a performance property rather than a behaviour:
+Two of the tests encode a performance property rather than a behavior:
 `test_egress.py` asserts on the SQL the ORM emits, and `test_history_window.py` asserts
 that the read cost stops growing with story length.
 
@@ -1150,7 +1151,7 @@ nobody has to discover them the hard way.
   lock) and the rate limiter in Redis.
 - **No vector index.** Retrieval does cosine similarity in Python over the whole bank. Fine
   at the 200-memory cap; at 10,000 it would want pgvector.
-- **Prompt snapshots are heavy** even after the egress fix — they're deferred, not smaller.
+- **Prompt snapshots are heavy** even after the egress fix; they're deferred, not smaller.
   Compressing them or expiring old ones is the real fix.
 - **In-memory rate-limit windows reset on restart**, so a restart grants a brief extra
   allowance.
@@ -1160,7 +1161,7 @@ nobody has to discover them the hard way.
   detect after the fact by string-matching the 429 body.
 - **The two memory marks are one pair on the adventure, not one per branch.** Switching
   lines makes the mark on the line being left unreadable from the new one, so that ground is
-  summarized again. It fails in the safe direction — redo, never skip — but switching back
+  summarized again. It fails in the safe direction: redo, never skip. But switching back
   and forth costs AI calls. Per-branch cursors are the fix if it matters.
 - **Story cards are adventure-wide**, so a card invented on one branch shows on all of them.
 - **Editing an already-summarized turn leaves its memory stale.** Replacing a turn withdraws
@@ -1168,8 +1169,8 @@ nobody has to discover them the hard way.
 
 ## Cleanup backlog
 
-`docs/self-review.md` carries an open list of non-bugs — reuse, simplification and
+`docs/self-review.md` carries an open list of non-bugs (reuse, simplification, and
-efficiency items — kept deliberately separate from the correctness list, which is empty.
+efficiency items) kept deliberately separate from the correctness list, which is empty.
 The largest ones:
 
 - `Section.tokens` is uncached, so the context gets tokenized two or three times a turn.

docs/self-review.md

@@ -1,72 +1,73 @@
 # Self-review log
 
-**Every correctness bug on this page is resolved** — 20 fixed, 1 intentionally skipped with the
+**Every correctness bug on this page is resolved.** 20 are fixed, and 1 is intentionally
-reasoning recorded below. The record is kept because the reasoning outlives the verdicts;
+skipped, with the reasoning recorded below. The record is kept because the reasoning outlives
-several of these are traps worth remembering. The *cleanup backlog* at the bottom is a
+the verdicts, and several of these are traps worth remembering. The *cleanup backlog* at the
-deliberately open list of non-bugs (reuse, simplification, efficiency), not outstanding defects.
+bottom is a deliberately open list of non-bugs (reuse, simplification, efficiency), not
+outstanding defects.
 
 Original review: 2026-07-05, whole project in scope (no git history at the time).
-Status key: `fixed` = applied, `skipped` = intentionally not fixed, `pending` = outstanding
+Status key: `fixed` means applied, `skipped` means intentionally not fixed, and `pending` means
-(none remain).
+outstanding (none remain).
 
-**2026-07-06 update (branch `bugfix-code-review`):** every finding re-verified against
+**2026-07-06 update (branch `bugfix-code-review`):** every finding was re-verified against
-current code. #1/#2/#3/#4/#6/#12 had already been fixed in earlier sessions (statuses were
+current code. #1, #2, #3, #4, #6, and #12 had already been fixed in earlier sessions, so their
-stale); #5/#7/#8/#9/#10/#13/#14 (backend) and #15–#21 (frontend) fixed in this pass.
+statuses were stale. #5, #7, #8, #9, #10, #13, #14 (backend) and #15 through #21 (frontend)
-#11 is skipped: real AI Dungeon's `addStoryCard` also returns the new card's index
+were fixed in this pass. #11 is skipped: real AI Dungeon's `addStoryCard` also returns the new
-(0-falsy included) per the official scripting guidebook, so changing it would break
+card's index (0-falsy included) per the official scripting guidebook, so changing it would
-compatibility — documented in `engine.py`'s prelude instead. The cleanup backlog
+break compatibility. This is documented in `engine.py`'s prelude instead. The cleanup backlog
 (R/S/E/A items) below remains open by design.
 
 ## Correctness bugs
 
 ### 1. [fixed] seed_demo.py doesn't stamp schema version → server crashes on next start
 - `backend/seed_demo.py:10`
-- Fresh DB created via `Base.metadata.create_all` leaves `PRAGMA user_version` at 0. Next server start sees tables exist, replays every ALTER TABLE migration → `duplicate column name` crash.
+- A fresh DB created via `Base.metadata.create_all` leaves `PRAGMA user_version` at 0. The next server start sees the tables exist and replays every ALTER TABLE migration, causing a `duplicate column name` crash.
 - Fix: stamp user_version to latest after create_all (reuse migrations.bootstrap logic).
 
 ### 2. [fixed] Turn-lock race: two simultaneous turns can run on the same adventure
 - `backend/app/routers/adventures.py:302`
-- `ensure_not_generating()` runs in the route handler but `_active_turns.add()` only happens when the StreamingResponse generator is first iterated. Double-click Continue → both requests pass the 409 check → duplicate Action.index rows, interleaved generations.
+- `ensure_not_generating()` runs in the route handler, but `_active_turns.add()` only happens when the StreamingResponse generator is first iterated. Double-clicking Continue sends both requests past the 409 check, producing duplicate Action.index rows and interleaved generations.
 - Fix: atomically test-and-set the lock in the request phase, release in the stream's `finally`.
 
 ### 3. [fixed] Migration 10 renumbers indexes with a correlated subquery on the table being updated
 - `backend/app/migrations.py:34`
-- SQLite may evaluate the subquery against partially-updated rows → duplicate indexes survive the "repair".
+- SQLite may evaluate the subquery against partially updated rows, so duplicate indexes can survive the "repair".
 - Fix: compute new indexes in Python (SELECT ordered, then UPDATE per row).
 
 ### 4. [fixed] SQLite foreign keys never enabled → CASCADE/SET NULL clauses are dead
 - `backend/app/database.py:8`
-- Deleting a Script leaves orphaned `scenario_scripts` rows; SQLite rowid reuse can attach a future script to an old scenario.
+- Deleting a Script leaves orphaned `scenario_scripts` rows. SQLite rowid reuse can then attach a future script to an old scenario.
 - Fix: `PRAGMA foreign_keys=ON` via engine connect event.
 
 ### 5. [fixed] Provider generate() silently yields nothing for non-SSE 200 responses
 - `backend/app/providers/openai_compatible.py:84`
-- Server that ignores `stream=true` and returns plain JSON → no `data:` lines → empty AI action, no error.
+- A server that ignores `stream=true` and returns plain JSON produces no `data:` lines, so the result is an empty AI action with no error.
-- Fix: buffer non-SSE body and fall back to parsing it as a single JSON completion.
+- Fix: buffer the non-SSE body and fall back to parsing it as a single JSON completion.
 
 ### 6. [fixed] Fire-and-forget asyncio task can be GC'd mid-run and wedge the memory bank
 - `backend/app/memorybank.py:146`
-- `asyncio.create_task` result not referenced; task can vanish silently; adventure ID can stay stuck in `_running`.
+- The result of `asyncio.create_task` is not referenced, so the task can vanish silently and leave an adventure ID stuck in `_running`.
 - Fix: keep strong refs in a set, discard in done-callback.
 
 ### 7. [fixed] Memory cursors are list positions but Memory.source_start/end are Action.index values
 - `backend/app/memorybank.py:213`
-- After any action deletion (indexes keep gaps, positions shift), summarization skips/duplicates blocks and `_update_story_summary` folds the wrong memories.
+- After any action deletion, indexes keep gaps and positions shift, so summarization skips or duplicates blocks and `_update_story_summary` folds the wrong memories.
-- Fix: use one space consistently — track cursors by Action.index (position-independent), or renumber on delete.
+- Fix: use one space consistently. Track cursors by Action.index (position-independent), or renumber on delete.
 
 ### 8. [fixed] Pinned memories don't count toward memory_top_k cap
 - `backend/app/memorybank.py:120`
-- 6 pinned + top_k=5 → 11 memories injected, blowing token budget.
+- 6 pinned plus top_k=5 injects 11 memories, blowing the token budget.
 - Fix: fill with unpinned only up to `top_k - len(pinned)` (min 0).
 
 ### 9. [fixed] Embedding-model change → cosine() zips different-dimension vectors silently
 - `backend/app/memorybank.py:69`
-- Old 768-dim embeddings scored against new 1536-dim query → garbage similarity, no error, never re-embedded.
+- Old 768-dimension embeddings scored against a new 1536-dimension query produce garbage similarity with no error, and are never re-embedded.
 - Fix: return 0.0 on length mismatch (and ideally clear stale embeddings so _embed_pending redoes them).
 
 ### 10. [fixed] MAX_STORY_CARDS cap is a no-op for cards created in one hook
 - `backend/app/scripting/pipeline.py:59`
-- `len(existing) + len(seen_ids) < MAX...` never counts newly added cards (seen_ids ⊂ existing). A script can insert unbounded cards in one turn.
+- `len(existing) + len(seen_ids) < MAX...` never counts newly added cards, since seen_ids is a subset of existing. A script can insert an unbounded number of cards in one turn.
 - Fix: count inserts made during the loop.
 
 ### 11. [skipped] addStoryCard returns 0 (falsy) for the first card, indistinguishable from `false` rejection
@@ -80,17 +81,17 @@ compatibility — documented in `engine.py`'s prelude instead. The cleanup backl
 
 ### 13. [fixed] test_connection 500s on non-dict JSON from /models
 - `backend/app/routers/settings.py:54`
-- Only ValueError caught; `data.get`/`m.get` on non-dict raises AttributeError → 500 instead of `{ok:false}`.
+- Only ValueError is caught. `data.get`/`m.get` on non-dict input raises AttributeError, producing a 500 instead of `{ok:false}`.
 - Fix: catch (ValueError, AttributeError, TypeError) or validate shapes.
 
 ### 14. [fixed] AI Dungeon exports with `worldInformation` key lose all story cards silently
 - `backend/app/routers/scenarios.py:133`
-- Import reads only `storyCards`/`worldInfo`; `worldInformation` is in _IGNORED_KEYS so it's dropped and not reported.
+- Import reads only `storyCards`/`worldInfo`. `worldInformation` is in _IGNORED_KEYS, so it is dropped without being reported.
 - Fix: accept `worldInformation` as a card source too.
 
 ### 15. [fixed] Shared debounce timer loses edits (Play PlotPanel)
 - `frontend/src/pages/Play.jsx:28`
-- One `saveTimer` shared by all plot fields AND story-card saves; editing a second thing within 600ms cancels the first pending PATCH → silent data loss.
+- One `saveTimer` is shared by all plot fields and story-card saves. Editing a second field within 600ms cancels the first pending PATCH, causing silent data loss.
 - Fix: per-key timers (e.g. a Map keyed by field/card id).
 
 ### 16. [fixed] Same shared-debounce data loss in ScenarioEditor
@@ -99,49 +100,50 @@ compatibility — documented in `engine.py`'s prelude instead. The cleanup backl
 
 ### 17. [fixed] Continue button silently discards typed input text
 - `frontend/src/pages/Play.jsx:469`
-- Clicking Continue with text in the box sends type 'continue' (backend ignores text) and clears the input.
+- Clicking Continue with text in the box sends type 'continue' (the backend ignores the text) and clears the input.
 - Fix: don't clear input on continue (or treat non-empty input as a normal send).
 
 ### 18. [fixed] retry() optimistically deletes last AI action with no rollback on failure
 - `frontend/src/pages/Play.jsx:475`
-- Failed retry (409/network) leaves UI missing an action that still exists server-side.
+- A failed retry (409 or network error) leaves the UI missing an action that still exists server-side.
 - Fix: restore the removed action in the catch path (or only remove on first stream event).
 
 ### 19. [fixed] Settings test()/save() have no error handling → stuck on "Testing…"
 - `frontend/src/pages/Settings.jsx:66`
-- Rejection leaves `{pending:true}` forever + unhandled rejection.
+- A rejection leaves `{pending:true}` forever and produces an unhandled rejection.
 - Fix: try/catch → setTestResult({ok:false, error:msg}).
 
 ### 20. [fixed] InsightsPanel race: slow earlier request overwrites newer report
 - `frontend/src/pages/Play.jsx:302`
-- No staleness guard; slow getAdventureContext can clobber a newer action snapshot.
+- There is no staleness guard, so a slow getAdventureContext call can overwrite a newer action snapshot.
-- Fix: track a request id / cancelled flag in the effect.
+- Fix: track a request id or cancelled flag in the effect.
 
 ### 21. [fixed] extractPlaceholders ignores ${...} in story-card trigger keys
 - `frontend/src/pages/Scenarios.jsx:50`
-- Backend fills placeholders in card.keys but the modal never prompts for those names → literal `${hero}` keys never match.
+- The backend fills placeholders in card.keys, but the modal never prompts for those names, so a literal `${hero}` key never matches.
 - Fix: also scan card.keys when collecting placeholder names.
 
 ## Cleanup backlog (reuse / simplification / efficiency / altitude — not bugs, apply later)
 
-- **R1** `frontend/src/pages/Play.jsx:26` + `ScenarioEditor.jsx:19` + `ScriptEditor.jsx:34` — three copies of the debounced-autosave + story-card handlers; extract a `useDebouncedSave` hook / shared StoryCardList component. (Fixing bugs #15/#16 properly may accomplish this.)
+- **R1** `frontend/src/pages/Play.jsx:26` + `ScenarioEditor.jsx:19` + `ScriptEditor.jsx:34`: three copies of the debounced-autosave and story-card handlers. Extract a `useDebouncedSave` hook and a shared StoryCardList component. Fixing bugs #15/#16 properly may accomplish this.
-- **R2** `backend/seed_demo.py:228` — re-implements create_adventure; call the router logic instead.
+- **R2** `backend/seed_demo.py:228`: re-implements create_adventure. Call the router logic instead.
-- **R3** `backend/app/providers/openai_compatible.py:122` — complete() duplicates _request() body building; add a `stream` param to _request().
+- **R3** `backend/app/providers/openai_compatible.py:122`: complete() duplicates _request()'s body building. Add a `stream` param to _request().
-- **R4** `backend/app/routers/adventures.py:476` — six copies of child-resource get+owner-check+404; extract `get_owned_or_404`.
+- **R4** `backend/app/routers/adventures.py:476`: six copies of child-resource get+owner-check+404. Extract `get_owned_or_404`.
-- **R5** `frontend/src/api.js:26` — streamSSE duplicates request()'s error extraction; extract `throwIfNotOk(resp)`.
+- **R5** `frontend/src/api.js:26`: streamSSE duplicates request()'s error extraction. Extract `throwIfNotOk(resp)`.
-- **S1** `backend/app/models.py:210` — `Settings.stream` is dead state (never read); delete column + schema fields.
+- **S1** `backend/app/models.py:210`: `Settings.stream` is dead state (never read). Delete the column and its schema fields.
-- **S2** `frontend/src/pages/Play.jsx:6` — MODES and PLAYER_TYPES are identical constants; lastIsAi/canUndo computed twice.
+- **S2** `frontend/src/pages/Play.jsx:6`: MODES and PLAYER_TYPES are identical constants; lastIsAi/canUndo are computed twice.
-- **E1** `backend/app/context/builder.py:119` — joins+tokenizes the ENTIRE adventure history every turn for the trigger window; walk reversed(actions) until budget instead.
+- **E1** `backend/app/context/builder.py:119`: joins and tokenizes the entire adventure history every turn for the trigger window. Walk reversed(actions) until budget instead.
-- **E2** `backend/app/scripting/pipeline.py:77` — rebuilds full history dicts + JSON + a blocking commit per script per hook; build once per hook, slice to HISTORY_WINDOW first, commit once.
+- **E2** `backend/app/scripting/pipeline.py:77`: rebuilds full history dicts, JSON, and a blocking commit per script per hook. Build once per hook, slice to HISTORY_WINDOW first, and commit once.
-- **E3** `frontend/src/pages/Play.jsx:561` — every SSE chunk re-renders all action rows; isolate streaming text in a child component / React.memo rows.
+- **E3** `frontend/src/pages/Play.jsx:561`: every SSE chunk re-renders all action rows. Isolate streaming text in a child component or React.memo rows.
-- **E4** `backend/app/context/builder.py:48` — Section.tokens uncached, whole context tokenized 2-3×/turn; cache counts, sum sections.
+- **E4** `backend/app/context/builder.py:48`: Section.tokens is uncached, so the whole context gets tokenized 2 to 3 times per turn. Cache counts and sum sections.
-- **E5** `frontend/src/pages/Play.jsx:490` — keydown effect has no dep array → listener re-registered every render.
+- **E5** `frontend/src/pages/Play.jsx:490`: the keydown effect has no dependency array, so the listener is re-registered every render.
-- **E6** `backend/app/memorybank.py:182` — catch-up summarization awaits blocks sequentially; gather independent blocks.
+- **E6** `backend/app/memorybank.py:182`: catch-up summarization awaits blocks sequentially. Gather independent blocks instead.
 - **A1** ~~no UniqueConstraint('adventure_id','index'); index allocation is ad-hoc per writer.~~
-  **Overtaken by phase 14 (2026-08).** `index` is a legacy column that nothing reads: ordering is
+  **Overtaken by phase 14 (2026-08).** `index` is a legacy column that nothing reads: ordering
-  `(branch_id, depth)` now, allocated in one place (`tree.place_action`). The column is kept unread
+  is `(branch_id, depth)` now, allocated in one place (`tree.place_action`). The column is kept
-  for one release and then dropped, so a constraint on it would be a constraint on a corpse.
+  unread for one release and then dropped, so a constraint on it would apply to a column that
-- **A2** `backend/app/providers/openai_compatible.py:45` — CHAT_CONTINUE_HINT appended below the budgeting layer; assemble prompts in context builder.
+  no longer does anything.
-- **A3** `backend/app/routers/adventures.py:390` — import endpoints hand-coerce raw dicts; use a Pydantic bundle schema.
+- **A2** `backend/app/providers/openai_compatible.py:45`: CHAT_CONTINUE_HINT is appended below the budgeting layer. Assemble prompts in the context builder instead.
-- **A4** `backend/app/routers/adventures.py:207` — onModelContext flattens (system, story) and ships everything as user content if modified; pass structure through the hook.
+- **A3** `backend/app/routers/adventures.py:390`: import endpoints hand-coerce raw dicts. Use a Pydantic bundle schema.
-- **A5** `frontend/src/pages/Home.jsx:87` — client appends 'Z' to naive datetimes; emit ISO-8601 with offset from the API instead.
+- **A4** `backend/app/routers/adventures.py:207`: onModelContext flattens (system, story) and ships everything as user content if modified. Pass structure through the hook instead.
+- **A5** `frontend/src/pages/Home.jsx:87`: the client appends 'Z' to naive datetimes. Emit ISO-8601 with an offset from the API instead.

frontend/README.md

@@ -13,4 +13,4 @@ The React Compiler is not enabled on this template because of its impact on dev
 
 ## Expanding the Oxlint configuration
 
-If you are developing a production application, we recommend using TypeScript with type-aware lint rules enabled. Check out the [TS template](https://github.com/vitejs/vite/tree/main/packages/create-vite/template-react-ts) for information on how to integrate TypeScript and Oxlint's TypeScript related rules in your project.
+If you are developing a production application, use TypeScript with type-aware lint rules enabled. See the [TS template](https://github.com/vitejs/vite/tree/main/packages/create-vite/template-react-ts) for how to integrate TypeScript and Oxlint's TypeScript-related rules in your project.