diff --git a/.github/workflows/deploy-web.yml b/.github/workflows/deploy-web.yml
new file mode 100644
index 0000000..f7c0b05
--- /dev/null
+++ b/.github/workflows/deploy-web.yml
@@ -0,0 +1,46 @@
+name: Deploy web client
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - "web/**"
+      - ".github/workflows/deploy-web.yml"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: github-pages
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 22
+          cache: npm
+          cache-dependency-path: web/package-lock.json
+      - run: npm ci
+        working-directory: web
+      - run: npm run build -- --base=/${{ github.event.repository.name }}/
+        working-directory: web
+      - uses: actions/upload-pages-artifact@v3
+        with:
+          path: web/dist
+
+  deploy:
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - id: deployment
+        uses: actions/deploy-pages@v4
diff --git a/.gitignore b/.gitignore
index d1fe164..ce83ce4 100644
--- a/.gitignore
+++ b/.gitignore
@@ -28,8 +28,11 @@ tools/julia/
 .pytest_cache
 .ruff_cache
 
-# Web dependencies and locally exported deployment models
+# Web dependencies and locally exported models. The verified public browser
+# policy below is the one exception: it is deliberately served as a static asset.
 web/node_modules/
 web/*.tsbuildinfo
 web/public/models/*.onnx
 web/public/models/*.json
+!web/public/models/jax-ppo.onnx
+!web/public/models/jax-ppo.json
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
new file mode 100644
index 0000000..b40991c
--- /dev/null
+++ b/.gitlab-ci.yml
@@ -0,0 +1,18 @@
+stages:
+  - deploy
+
+deploy-pages:
+  stage: deploy
+  image: node:22
+  rules:
+    - if: $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH
+      changes:
+        - web/**/*
+        - .gitlab-ci.yml
+  script:
+    - cd web
+    - npm ci
+    - npm run build -- --base="${CI_PAGES_URL}/"
+    - mv dist ../public
+  pages:
+    publish: public
diff --git a/AGENTS.md b/AGENTS.md
index f69b4fb..c1d8a80 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,444 +1,98 @@
 # AGENTS.md
 
-This repository is managed with `uv`. Use `uv run ...` for commands so the
-project environment and Cython extensions are built/loaded consistently.
+This repository is managed with `uv`. Use `uv run ...` so the project
+environment and Cython extensions are built and loaded consistently.
 
-## Project Layout
+## Active project path
 
-- `src/coolrl_lost_cities/games/classic/game.pyx`: Cython Lost Cities engine.
-- `src/coolrl_lost_cities/games/classic/deep_cfr/`: Deep CFR training,
-  traversal, evaluation, analysis, and CLI code.
-- `configs/deep_cfr/`: active Deep CFR YAML configs (kebab-case filenames).
-  Currently holds two:
-  - `default.yaml`: the canonical "best-known" baseline. Start here, then
-    override fields via `--set` for experiments/ablations.
-  - `smoke.yaml`: 1-iter sanity check for the training loop.
-- `configs/archive/`: retired/historical configs. Don't modify; reference
-  if you need to reproduce an old run.
-- `runs/`: generated training runs. Gitignored, may be a symlink to larger
-  storage. Layout:
-  - `runs/archive/`: past runs. **Do not modify or delete.**
-  - `runs/tmp/`: smoke, tests, throwaway. Free to `rm -rf` anytime.
-  - `runs/<YYYY-MM-DD_HHMMSS>_<kebab-name>/`: real experiments (flat).
-  Promote a `runs/<...>` directory to `runs/archive/` with a manual `mv`
-  once analysis is complete.
-- `docs/`: profiling notes, migration notes, and experiment documentation.
+The active product and research path is **JAX + PPO**:
 
-## Core Commands
+- `src/lost_cities_jax/`: pure JAX rules, observations, PPO, evaluation,
+  league, and human-play tools.
+- `configs/jax_ppo/`: active YAML configurations.
+- `web/`: static TypeScript client with the final JAX PPO ONNX policy.
+- `web/public/models/jax-ppo.onnx`: verified browser policy. Keep its manifest
+  in sync and do not replace it without running the export validation.
 
-Run lint:
+Historical Deep CFR and ISMCTS implementations live under
+`src/coolrl_lost_cities/games/classic/`. Their configs are in `legacy/`; they
+are reproduction-only and must not be used as the default for new work. See
+`docs/legacy.md`.
+
+## Core commands
 
 ```bash
 uv run ruff check .
-```
-
-Run all tests:
-
-```bash
+uv run pytest -q tests/lost_cities_jax
 uv run pytest -q
+uv run lost-cities-jax-ppo --help
 ```
 
-Run focused Deep CFR tests:
+Web checks:
 
 ```bash
-uv run pytest -q tests/games/classic/test_deep_cfr_trainer.py
+cd web
+npm test
+npm run build
 ```
 
-Run the CLI through the console script:
+## JAX PPO workflow
+
+CPU smoke runs write disposable artifacts under `runs/tmp/`:
 
 ```bash
-uv run lost-cities-deep-cfr --help
+uv run lost-cities-jax-ppo rollout-smoke --config configs/jax_ppo/smoke.yaml
+uv run lost-cities-jax-ppo train --config configs/jax_ppo/smoke.yaml
 ```
 
-Equivalent module form:
+GPU training must hold the shared compute lock. Use a real `tmux` session for
+long user-observable jobs:
 
 ```bash
-uv run python -m coolrl_lost_cities.games.classic.deep_cfr.cli --help
+flock -n .compute.lock uv run --with 'jax[cuda12]' lost-cities-jax-ppo train \
+  --config configs/jax_ppo/balanced.yaml \
+  --set run.artifact_root=runs/jax-ppo
 ```
 
-## Deep CFR Training
-
-The CLI auto-derives the run directory from `run.experiment_name` plus a
-timestamp. By default runs land under `runs/tmp/`; pass `--keep` for a real
-experiment that should live under `runs/`.
-
-Smoke / throwaway run (lands in `runs/tmp/`):
+Evaluation is deterministic and does not need the lock:
 
 ```bash
-uv run lost-cities-deep-cfr train --config configs/deep_cfr/smoke.yaml
-# → runs/tmp/<YYYY-MM-DD_HHMMSS>_smoke/
+uv run lost-cities-jax-ppo eval \
+  --config configs/jax_ppo/balanced.yaml \
+  --checkpoint runs/jax-ppo/<run>/latest \
+  --opponent heuristic_balanced --games 10000 --duplicate
 ```
 
-Real experiment (lands in `runs/`):
+Generated artifacts under `runs/` are gitignored. Do not modify or delete
+`runs/archive/`.
+
+## Static browser policy
+
+The checked-in ONNX policy is small enough for static distribution. To replace
+it, export a validated checkpoint and rebuild the web app:
 
 ```bash
-uv run lost-cities-deep-cfr train \
-  --config configs/deep_cfr/default.yaml \
-  --keep
-# → runs/<YYYY-MM-DD_HHMMSS>_deep-cfr-default/
+uv run --with onnx scripts/export_jax_ppo_onnx.py \
+  --checkpoint /path/to/checkpoint \
+  --output web/public/models/jax-ppo.onnx
+cd web && npm test && npm run build
 ```
 
-Variant / ablation (override one field; keep slug informative):
+Commit the ONNX file and its JSON manifest together. The app must continue to
+use a base-relative model URL so static subpath hosts work.
 
-```bash
-uv run lost-cities-deep-cfr train \
-  --config configs/deep_cfr/default.yaml \
-  --keep \
-  --set training_weighting.mode=none \
-  --set run.experiment_name=ablation-no-lcfr
-# → runs/<YYYY-MM-DD_HHMMSS>_ablation-no-lcfr/
-```
+## Documentation
 
-Short fixed-iteration run:
+- Active plans: `docs/plans/`.
+- Retired plans and historical evidence: `docs/plans/archive/`,
+  `docs/archive/`, and `docs/research/`.
+- Do not edit archival documents; add a new dated note or active plan instead.
 
-```bash
-uv run lost-cities-deep-cfr train \
-  --config configs/deep_cfr/default.yaml \
-  --set run.max_iterations=100 \
-  --set checkpoint.save_every=0
-```
+When changing docs, run `scripts/librarian.sh` to validate Markdown links and
+`file:line` citations.
 
-Resume (path required, no shortcut):
+## Git policy
 
-```bash
-uv run lost-cities-deep-cfr train \
-  --config configs/deep_cfr/default.yaml \
-  --resume runs/<YYYY-MM-DD_HHMMSS>_<slug>/latest.pt
-```
-
-When `--resume` is given, the trainer reuses the resumed checkpoint's parent
-directory; no new timestamped folder is created.
-
-Useful train controls:
-
-- `--keep`: real experiment, write under `runs/` (default is `runs/tmp/`).
-- `--resume PATH`: resume from a specific checkpoint. `PATH` is required.
-- `--set PATH=VALUE`: override config fields. Repeatable, parses values as
-  YAML (e.g. `--set traversal.num_workers=4`, `--set run.max_minutes=null`).
-
-Common `--set` overrides:
-
-- `--set run.device=cuda`: set the trainer device.
-- `--set run.experiment_name=foo-v2`: change the slug used in the run dir
-  name (kebab-case).
-- `--set checkpoint.exact_resume=true`: require checkpoint config compatibility.
-- `--set checkpoint.save_latest=false --set checkpoint.save_every=0`:
-  disable checkpoint writes.
-- `--set checkpoint.save_every=0`: keep only `latest.pt` (no archives).
-- `--set checkpoint.save_every=N`: archive every N iterations.
-
-## Naming Conventions
-
-- **Directory names, run dirs, config filenames, `experiment_name` values**:
-  kebab-case (`deep-cfr-color-shared-512x3.yaml`,
-  `runs/2026-05-08_103045_color-attn-v2/`).
-- **YAML keys, Python identifiers, config field names**: snake_case
-  (unchanged: `hidden_size`, `traversals_per_player`, `experiment_name`).
-- The CLI converts `run.experiment_name` to a kebab slug when building the
-  run directory, so values may contain spaces or mixed case.
-
-## Long Runs
-
-Run long jobs in a real `tmux` session so the user can attach and stop them.
-Do not rely on Codex command sessions for long user-observable training runs.
-
-Start a long unbounded run:
-
-```bash
-tmux new-session -s coolrl-deepcfr-unbounded \
-  -c /home/coolguy/dev/coolrl-lost-cities \
-  'uv run lost-cities-deep-cfr train \
-    --config configs/deep_cfr/default.yaml \
-    --set run.max_iterations=null \
-    --set run.max_minutes=null \
-    --keep'
-```
-
-Attach later:
-
-```bash
-tmux attach -t coolrl-deepcfr-unbounded
-```
-
-Detach without stopping:
-
-```text
-Ctrl+B, D
-```
-
-Stop training:
-
-```text
-Ctrl+C
-```
-
-Follow logs from another terminal:
-
-```bash
-tail -f runs/<YYYY-MM-DD_HHMMSS>_<slug>/train.log
-```
-
-The unbounded config intentionally has:
-
-```yaml
-run:
-  max_iterations: null
-  max_minutes: null
-checkpoint:
-  save_every: 100
-```
-
-`latest.pt` is updated continuously; archive checkpoints are written every 100
-iterations. If disk is tight, set `--set checkpoint.save_every=0` (keep only
-`latest.pt`) or increase `save_every`.
-
-## Compute Lock
-
-여러 에이전트가 한 머신을 공유하므로, train과 속도 벤치마크는
-repo 루트 `.compute.lock`을 잡고 실행한다:
-
-```bash
-flock -n .compute.lock uv run lost-cities-deep-cfr train ...
-```
-
-승률/점수만 뽑는 eval과 `analyze`는 결정적이라 락 불필요.
-
-## Evaluation And Analysis
-
-Evaluate a checkpoint:
-
-```bash
-uv run lost-cities-deep-cfr eval \
-  --checkpoint runs/<run-dir>/latest.pt \
-  --opponent random \
-  --games 100 \
-  --device cpu
-```
-
-Save evaluation game records:
-
-```bash
-uv run lost-cities-deep-cfr eval \
-  --checkpoint runs/<run-dir>/latest.pt \
-  --opponent random \
-  --games 100 \
-  --device cpu \
-  --save-games runs/<run-dir>/eval_random_games.json
-```
-
-Generate analysis plots from `metrics.jsonl`:
-
-```bash
-uv run lost-cities-deep-cfr analyze \
-  --run runs/<run-dir>
-```
-
-Write plots to a separate directory:
-
-```bash
-uv run lost-cities-deep-cfr analyze \
-  --run runs/<run-dir> \
-  --output-dir runs/<run-dir>/analysis
-```
-
-The analyzer reads `metrics.jsonl` and writes PNG files grouped by diagnostic
-section. Opponents are compared within each plot using fixed colors. The
-`lost-cities-deep-cfr analyze` subcommand uses the analyzer default smoothing
-window, currently 1 iteration (no smoothing), and supports `--max-iteration`.
-
-For smoothing controls, run the analyzer module directly:
-
-```bash
-uv run python -m coolrl_lost_cities.games.classic.deep_cfr.analyze \
-  --run runs/<run-dir> \
-  --smoothing-window 5
-```
-
-Use `--no-smoothing` to force no moving average.
-
-Current output files:
-
-- `analysis_01_loss.png`
-- `analysis_02_match.png`
-- `analysis_03_action.png`
-- `analysis_04_gameflow.png`
-- `analysis_05_open_quality.png`
-- `analysis_06_expedition_outcomes.png`
-- `analysis_07_calibration.png`
-- `analysis_08_traversal.png`
-- `analysis_09_selectivity.png`
-- `analysis_final_eval_summary.png`
-
-## Runtime Artifacts
-
-Each training run writes:
-
-- `metrics.jsonl`: structured metrics, one completed iteration per line.
-- `train.log`: human-readable timestamped logs.
-- `runtime_progress.json`: latest progress snapshot.
-- `latest.pt`: latest checkpoint.
-- `iteration_*.pt`: archive checkpoints when enabled.
-- `config.json`: resolved config for the run.
-
-If a run is stopped mid-iteration, the in-progress iteration may not appear in
-`metrics.jsonl`. Analyze the latest completed metric row.
-
-## Weights & Biases (Optional)
-
-Metrics can be mirrored to W&B. `wandb` is an optional extra; default
-installs and runs do not require it.
-
-Install:
-
-```bash
-uv sync --extra wandb
-```
-
-Run with W&B:
-
-```bash
-# Offline: no login, writes to <run_dir>/wandb/offline-run-*/
-uv run lost-cities-deep-cfr train --config <...> --wandb --wandb-mode offline
-
-# Online: requires `uv run wandb login` once, then real-time upload
-uv run lost-cities-deep-cfr train --config <...> --wandb
-```
-
-W&B data is stored **per run** at `<run_dir>/wandb/`, not at a global
-`runs/wandb/`. Each training run gets its own subfolder, so moving or
-deleting a run directory carries its W&B data along with it.
-
-Sync offline runs to wandb.ai later:
-
-```bash
-wandb sync runs/<run-dir>/wandb/offline-run-*
-```
-
-Flags:
-
-- `--wandb`: enable W&B mirroring.
-- `--wandb-project <name>`: defaults to `coolrl-lost-cities`.
-- `--wandb-name <name>`: W&B run name; defaults to `run.experiment_name`.
-- `--wandb-mode {online,offline,disabled}`: default `online`.
-- `--wandb-group <name>`: group related runs from one experiment/hypothesis.
-- `--wandb-job-type <type>`: role of this run, e.g. `train`, `eval`, `sweep`, or `smoke`.
-- `--wandb-tag <tag>`: tag the run; repeatable.
-
-W&B is purely additive — `metrics.jsonl` remains the source of truth, and
-`analyze` reads `metrics.jsonl`, not W&B. Disabling W&B never breaks
-training, resume, or analysis.
-
-### Groups, notes, and tags
-
-Use `--wandb-group` for the experiment or hypothesis family, e.g.
-`model-size-grid-2026-05-08` or `strict-curriculum-v1`. Use `--wandb-name`
-for the individual run, e.g. `512x3-seed79`, and `--wandb-job-type` for the
-run role (`train`, `eval`, `sweep`, `smoke`).
-
-Use `--wandb-notes` for the run's *purpose* (free-form prose) and `--wandb-tag`
-for *categories you might filter on later* (short kebab-case keywords,
-repeatable). Otherwise use them however you like. Just avoid:
-
-- Tags that duplicate `config` (`lr-1e-4`, `traversal-280`) — W&B already
-  indexes config fields.
-- Tags that are unique per run (`test-1`, `2026-05-07`) — that's the run
-  name and timestamp's job.
-- Tag-as-sentence (`tested-bigger-traversal-with-lcfr`) — that belongs in
-  `--wandb-notes`.
-
-**Notes length**: 3–5 lines, commit-message-body length. Should answer
-*why* (hypothesis), *what* (key config delta), and *baseline* (run/iter
-to compare against). Long analyses go in `docs/` and are linked from
-notes; don't paste them in.
-
-### Comparing two runs
-
-Default is **sequential, single seed**. Run baseline first, then the
-treatment with exactly one config change, both with the same `run.seed`.
-Put both in the same W&B group (e.g. `--wandb-group lr-bump-v1`) and optionally
-tag both with a shared hypothesis tag (e.g. `--wandb-tag lr-bump`) so they show
-up together in W&B's Compare Runs view.
-
-Do **not** run multiple seeds per condition unless explicitly asked —
-that doubles or quintuples wall-clock and isn't the default protocol.
-Single-seed comparison is enough to surface a signal; multi-seed is a
-follow-up to confirm it.
-
-Do **not** run two trainings in parallel on the same GPU — VRAM/SM
-contention slows both unevenly and breaks the comparison.
-
-## Docs & Experiment Workflow
-
-### Where to write what
-
-| 기록 내용 | 쓸 곳 |
-| --- | --- |
-| 진행 중인 계획/가설 | `docs/plans/<topic>.md` (1 주제 1 파일) |
-| 끝난 계획 | `docs/plans/archive/` (수동 `mv`) |
-| 날짜 박힌 실험 기록 | `docs/archive/<name>-YYYY-MM-DD.md` (immutable) |
-| 항구적 알고리즘 노트 | `docs/research/<name>.md` (`Last verified:` 헤더) |
-| 비용/프로파일 | `docs/reports/<name>-YYYY-MM-DD.md` (dated) |
-| 스크래치 / 연구 스레드 인덱스 | `ideas.md` |
-
-Catalog of current research notes: [docs/research/README.md](docs/research/README.md).
-
-### Rules
-
-- `docs/archive/`, `runs/archive/`는 read-only.
-- archive 본문 복붙 금지 — 대신 `Source:` 링크 + distill.
-- `file.py:NN` 인용은 작성 시점에 `rg`로 검증.
-- 한 주제 한 파일 — `foo-v2.md` 만들지 말 것.
-- 파일당 ~500줄 soft cap — 강제 분할이 아니라 "다른 위치(archive/research)로
-  가야 할 내용이 누적됐는지" routing 점검 트리거. 초과 시 dated 실험은
-  `docs/archive/`로, 항구적 분석은 `docs/research/`로 보내고 본 파일은
-  현재 상태 reference만 남긴다.
-
-## Notes For Future Agents
-
-- Prefer `rg`/`rg --files` for search.
-- Use `apply_patch` for manual edits.
-- Do not commit generated run artifacts from `runs/`.
-- Cython-generated `.c` files are gitignored; edit `.pyx`/`.pxd` sources.
-- Before committing, run `uv run ruff check .` and at least the relevant pytest
-  subset. For Deep CFR changes, run
-  `uv run pytest -q tests/games/classic/test_deep_cfr_trainer.py`.
-- When changing docs, run `scripts/librarian.sh` to lint markdown link
-  integrity and `file:line` code citations across `docs/**`. See
-  `docs/plans/librarian.md` for the full design.
-
-## Git Branching Policy (READ THIS)
-
-**DO NOT create new git branches unless the user explicitly asks for one in
-the current task. Work on whatever branch is currently checked out (default
-`main`). This is a hard rule — no exceptions for "safety", "isolation",
-"experiments", "work-in-progress", or any other self-justified reason.**
-
-Why this rule exists:
-- This project intentionally develops on `main` with frequent small commits.
-- Auto-created branches like `experiments/foo`, `feature/bar`, `wip/baz`
-  fragment review, hide work from the user, and require manual cleanup.
-- The user has not authorized branch creation as a default behavior. If
-  they want a branch, they will say so explicitly ("make a branch", "PR
-  this", "isolate this in a branch", etc.).
-
-What you MUST do instead:
-- Make commits directly on the currently checked-out branch.
-- If you think a branch is justified, **stop and ask the user first** —
-  do not preemptively create one.
-- If a tool or subagent invocation auto-suggests creating a branch
-  (e.g. PR-style workflows), refuse the branch creation step and commit
-  to the current branch.
-- If you find yourself already on a non-default branch you didn't expect,
-  stop and ask the user — do not switch, do not create a new one, do not
-  reset.
-
-Forbidden without explicit user instruction:
-- `git checkout -b <name>`
-- `git switch -c <name>`
-- `git branch <name>`
-- `gh pr create` from an auto-created branch
-- Any worktree creation that implicitly creates a new branch
-
-This rule applies to the main agent and to every subagent or tool the main
-agent invokes. Pass it through in subagent prompts when delegating
-git-touching work.
+Do not create git branches unless the user explicitly asks in the current
+task. Work on the checked-out branch. Before committing, run `uv run ruff
+check .` and the relevant tests. Never commit generated run artifacts.
diff --git a/README.md b/README.md
index b506d19..467ec64 100644
--- a/README.md
+++ b/README.md
@@ -1,56 +1,68 @@
 # coolrl-lost-cities
 
-Focused Lost Cities extraction from the legacy `coolrl` repository.
+JAX PPO training and on-device browser play for the two-player card game Lost
+Cities. The project provides a pure JAX rules engine, PPO training and
+evaluation tools, and a static web client that runs the shipped final policy
+with WebGPU when available and WebAssembly otherwise.
 
-The current implementation starts with the classic two-player card game:
+The active path is **JAX + PPO**. Deep CFR and ISMCTS are retained only as
+historical research implementations; see [legacy notes](docs/legacy.md).
 
-- classic 5-expedition rules by default
-- Python/Cython game engine
-- env wrapper
-- random, discard-only, and safe-heuristic bots
-- core rule, scoring, mask, env, canonical-state, bot, and GUI smoke tests
+## Quick start
 
-Training code, Deep CFR, learned-policy evaluation, desktop GUI, and an
-on-device web client now live alongside the original rules port.
-
-## Development
+Install the project, then run a complete CPU-sized sanity check:
 
 ```bash
-uv run pytest tests/games/classic
-uv run lost-cities-classic
+uv sync
+uv run lost-cities-jax-ppo rollout-smoke --config configs/jax_ppo/smoke.yaml
+uv run lost-cities-jax-ppo train --config configs/jax_ppo/smoke.yaml
 ```
 
-For future GUI work, install the optional GUI dependencies:
+The final command prints a run directory containing `latest`, `config.json`,
+and `metrics.jsonl` under `runs/tmp/jax-ppo-artifacts/`.
+
+## Train and evaluate a PPO policy
+
+The committed configurations describe the opponent and training budget. For a
+GPU run, use CUDA JAX and keep generated artifacts outside git:
 
 ```bash
-uv sync --extra gui
+flock -n .compute.lock uv run --with 'jax[cuda12]' lost-cities-jax-ppo train \
+  --config configs/jax_ppo/balanced.yaml \
+  --set run.artifact_root=runs/jax-ppo
 ```
 
-Run the classic pygame GUI:
+Evaluate a saved checkpoint against a fixed opponent. Duplicate evaluation
+swaps seats over the same shuffled games:
 
 ```bash
-uv run lost-cities-classic-gui --mode pvc --bot safe-heuristic
+uv run lost-cities-jax-ppo eval \
+  --config configs/jax_ppo/balanced.yaml \
+  --checkpoint runs/jax-ppo/<run>/latest \
+  --opponent heuristic_balanced \
+  --games 10000 \
+  --duplicate
 ```
 
-The GUI uses the in-process Cython game engine.
+Run `uv run lost-cities-jax-ppo --help` for training against saved opponents,
+league runs, gates, human-play logs, and evaluation variants.
 
-## On-device Web Client
+## Browser client
 
-The `web/` app runs its TypeScript rules engine and exported JAX PPO policy
-entirely in the browser. It prefers WebGPU and falls back to WebAssembly.
-
-Export a local Orbax checkpoint and start Vite:
+The final verified JAX PPO policy is shipped as a 3.1 MB static ONNX asset.
+No server or local checkpoint is required to play it:
 
 ```bash
-uv run --with onnx scripts/export_jax_ppo_onnx.py \
-  --checkpoint /path/to/checkpoint \
-  --output web/public/models/jax-ppo.onnx
 cd web
-npm install
+npm ci
 npm run dev
 ```
 
-See [web/README.md](web/README.md) for tests and model parity tooling.
+`npm run build` produces a fully static site. The model path is deployment-base
+aware, so the build can be served from GitHub Pages, GitLab Pages, or a normal
+web root. Pushes to `main` deploy that build to both configured Pages hosts.
+See [web/README.md](web/README.md) for model replacement, tests, and the
+cross-runtime parity fixture.
 
 ## JAX Rules Engine
 
diff --git a/docs/legacy.md b/docs/legacy.md
new file mode 100644
index 0000000..bbf17b2
--- /dev/null
+++ b/docs/legacy.md
@@ -0,0 +1,25 @@
+# Legacy research stacks
+
+The supported project path is the JAX rules engine and JAX PPO tooling exposed
+by `lost-cities-jax-ppo`. The historical Deep CFR and ISMCTS implementations
+are preserved for research reproduction, but they are not current training
+recipes and no longer have public console-script entry points.
+
+## What is preserved
+
+- Deep CFR sources: `src/coolrl_lost_cities/games/classic/deep_cfr/`
+- ISMCTS sources: `src/coolrl_lost_cities/games/classic/ismcts/`
+- Their retired configurations: `legacy/deep-cfr/configs/` and
+  `legacy/ismcts/configs/`
+- Earlier plans and dated findings: `docs/plans/archive/`, `docs/archive/`,
+  and `docs/research/`
+
+These files remain in the repository so a historical experiment can be read or
+reproduced against its original commit. They should not be chosen for new
+models, benchmarks, or product work.
+
+## Current workflow
+
+Start from `configs/jax_ppo/`, run `lost-cities-jax-ppo`, and use the browser
+client in `web/`. The root [README](../README.md) contains the short training,
+evaluation, and static-web recipes.
diff --git a/docs/performance.md b/docs/performance.md
index fff6a9c..167ce13 100644
--- a/docs/performance.md
+++ b/docs/performance.md
@@ -1,7 +1,10 @@
-# Deep CFR Performance Notes
+# Legacy Deep CFR Performance Notes
 
-This document tracks current runtime bottlenecks for the active Deep CFR
-training path. The numbers below are observational, not a benchmark contract.
+> Historical record only. The supported training stack is JAX PPO; see the
+> root [README](../README.md) and [legacy notes](legacy.md).
+
+This document records the Deep CFR runtime bottlenecks observed before the JAX
+PPO transition. The numbers below are historical, not a benchmark contract.
 
 ## Current Default Runtime
 
@@ -11,7 +14,7 @@ Source run:
 runs/tmp/2026-05-07_171535_deep-cfr-default/metrics.jsonl
 ```
 
-The run used `configs/deep_cfr/default.yaml` with CUDA enabled. At the time of
+The run used `legacy/deep-cfr/configs/default.yaml` with CUDA enabled. At the time of
 inspection, completed metrics covered iterations 70 through 95. The training
 process was still running, so later rows may differ.
 
@@ -88,7 +91,7 @@ This gives 560 traversals per iteration, split into 70 worker batches.
 ## Device Use
 
 The trainer constructs the advantage and strategy networks on `run.device`.
-`configs/deep_cfr/default.yaml` sets:
+`legacy/deep-cfr/configs/default.yaml` sets:
 
 ```yaml
 run:
diff --git a/docs/plans/deep-cfr-selectivity.md b/docs/plans/archive/deep-cfr-selectivity.md
similarity index 100%
rename from docs/plans/deep-cfr-selectivity.md
rename to docs/plans/archive/deep-cfr-selectivity.md
diff --git a/docs/plans/librarian.md b/docs/plans/archive/librarian.md
similarity index 99%
rename from docs/plans/librarian.md
rename to docs/plans/archive/librarian.md
index 4aa884a..84af35b 100644
--- a/docs/plans/librarian.md
+++ b/docs/plans/archive/librarian.md
@@ -117,7 +117,7 @@ operator applies the patch.
 
 - ✅ AGENTS.md "Docs & Experiment Workflow" section landed
   (commit `09d5815`, 2026-05-07).
-- ✅ Plan drafted at `docs/plans/librarian.md` (this file).
+- ✅ Plan drafted at `docs/plans/archive/librarian.md` (this file).
 - ✅ Prompt moved: `.claude/agents/librarian.md` →
   `scripts/librarian-prompt.md`. Claude-specific subagent registration
   removed.
diff --git a/docs/plans/model_size_experiment.md b/docs/plans/archive/model_size_experiment.md
similarity index 98%
rename from docs/plans/model_size_experiment.md
rename to docs/plans/archive/model_size_experiment.md
index 5df93d6..88e22a0 100644
--- a/docs/plans/model_size_experiment.md
+++ b/docs/plans/archive/model_size_experiment.md
@@ -1,11 +1,11 @@
 # Plan: Model-Size Experiment (Keystone for Model-Scale Optimizations)
 
 > **⚠️ 스택 주의 — 이 문서는 Deep CFR / PyTorch 스택 전용이다.**
-> `input_dim=365`, `configs/deep_cfr/`, `DeepCFRMLP` 기준으로 쓰였다.
+> `input_dim=365`, `legacy/deep-cfr/configs/`, `DeepCFRMLP` 기준으로 쓰였다.
 > 현행 JAX PPO 스택(`OBS_DIM=454`, `configs/jax_ppo/`, `ActorCritic`)에는
 > **적용되지 않는다.** PPO 쪽 모델 크기 문제는
-> [jax-ppo-model-size-ab.md](jax-ppo-model-size-ab.md)와
-> [../reports/jax-ppo-model-capacity-2026-07-12.md](../reports/jax-ppo-model-capacity-2026-07-12.md)를 볼 것.
+> [jax-ppo-model-size-ab.md](../jax-ppo-model-size-ab.md)와
+> [../../reports/jax-ppo-model-capacity-2026-07-12.md](../../reports/jax-ppo-model-capacity-2026-07-12.md)를 볼 것.
 
 **Status:** Ready to execute
 **Owner:** Operator (runs grid on `home`); Codex (adds configs and runner script)
diff --git a/docs/plans/option_b_interleaved_traversal.md b/docs/plans/archive/option_b_interleaved_traversal.md
similarity index 100%
rename from docs/plans/option_b_interleaved_traversal.md
rename to docs/plans/archive/option_b_interleaved_traversal.md
diff --git a/docs/plans/torch_compile.md b/docs/plans/archive/torch_compile.md
similarity index 100%
rename from docs/plans/torch_compile.md
rename to docs/plans/archive/torch_compile.md
diff --git a/docs/plans/jax-ppo-model-size-ab.md b/docs/plans/jax-ppo-model-size-ab.md
index 40c2d6a..98019fd 100644
--- a/docs/plans/jax-ppo-model-size-ab.md
+++ b/docs/plans/jax-ppo-model-size-ab.md
@@ -7,8 +7,8 @@
 **Background:** [docs/reports/jax-ppo-model-capacity-2026-07-12.md](../reports/jax-ppo-model-capacity-2026-07-12.md)
 
 > 이 계획은 은퇴한 Deep CFR/PyTorch 스택용
-> [model_size_experiment.md](model_size_experiment.md)를 **대체하지 않는다** —
-> 그쪽은 다른 스택(`input_dim=365`, `configs/deep_cfr/`) 이야기다. 서로 무관하다.
+> [model_size_experiment.md](archive/model_size_experiment.md)를 **대체하지 않는다** —
+> 그쪽은 다른 스택(`input_dim=365`, `legacy/deep-cfr/configs/`) 이야기다. 서로 무관하다.
 
 ## 가설
 
diff --git a/docs/reports/final-cycles-and-human-play-2026-07-05.md b/docs/reports/final-cycles-and-human-play-2026-07-05.md
index 109b351..5358ee9 100644
--- a/docs/reports/final-cycles-and-human-play-2026-07-05.md
+++ b/docs/reports/final-cycles-and-human-play-2026-07-05.md
@@ -80,4 +80,4 @@ Validation performed before final report:
 - `uv run pytest -q` passed: 257 passed, 1 skipped.
 - `uv run lost-cities-jax-ppo play --help` passed.
 - `uv run lost-cities-jax-ppo human-play summarize --log-dir /tmp/nonexistent-human-play-log` passed.
-- `scripts/librarian.sh` found no link or code-citation errors; it still exits non-zero on the known pre-existing `docs/plans/deep-cfr-selectivity.md` 500-line soft cap.
+- `scripts/librarian.sh` found no link or code-citation errors; it still exits non-zero on the known pre-existing `docs/plans/archive/deep-cfr-selectivity.md` 500-line soft cap.
diff --git a/docs/reports/jax-ppo-model-capacity-2026-07-12.md b/docs/reports/jax-ppo-model-capacity-2026-07-12.md
index c38754d..b33c362 100644
--- a/docs/reports/jax-ppo-model-capacity-2026-07-12.md
+++ b/docs/reports/jax-ppo-model-capacity-2026-07-12.md
@@ -23,8 +23,8 @@ Metrics: `.../final-cycles/2026-07-05/league/2026-07-05_191933_jax-ppo-final-cyc
 (`main_ppo_config.json` → `network: {hidden_size: 512, num_layers: 3}`).
 
 `hidden_size`를 다룬 기존 문서는 전부 은퇴한 Deep CFR/PyTorch 스택 것이다
-(`input_dim=365`, `configs/deep_cfr/` 기준). 특히
-[docs/plans/model_size_experiment.md](../plans/model_size_experiment.md)는
+(`input_dim=365`, `legacy/deep-cfr/configs/` 기준). 특히
+[docs/plans/model_size_experiment.md](../plans/archive/model_size_experiment.md)는
 **현 JAX PPO 스택과 무관하다.**
 
 → 512×3은 실험으로 고른 값이 아니라 구 스택에서 복사돼 온 값이다.
diff --git a/docs/research/deep-cfr-performance-experiments.md b/docs/research/deep-cfr-performance-experiments.md
index c80cd2c..77eb754 100644
--- a/docs/research/deep-cfr-performance-experiments.md
+++ b/docs/research/deep-cfr-performance-experiments.md
@@ -54,5 +54,5 @@ The 8-worker interleaved path is more effective than a single-process CUDA path
 
 - `src/coolrl_lost_cities/games/classic/deep_cfr/trainer.py`: Implementation of AMP and training loops.
 - `src/coolrl_lost_cities/games/classic/deep_cfr/networks.py`: `DeepCFRMLP` architecture.
-- `configs/deep_cfr/default.yaml`: Configuration for interleaved scheduler.
-- `scripts/profile_gpu_forward.py`: GPU forward pass micro-benchmarks.
\ No newline at end of file
+- `legacy/deep-cfr/configs/default.yaml`: Configuration for interleaved scheduler.
+- `scripts/profile_gpu_forward.py`: GPU forward pass micro-benchmarks.
diff --git a/docs/research/optimization_sequencing.md b/docs/research/optimization_sequencing.md
index ee95abf..6f4eaa1 100644
--- a/docs/research/optimization_sequencing.md
+++ b/docs/research/optimization_sequencing.md
@@ -6,10 +6,10 @@
 
 | Lever | 어디서 nail되는지 | 현재 상태 |
 | --- | --- | --- |
-| **Model size growth** (hidden ≥ 1024 / layers ≥ 6) | `docs/plans/model_size_experiment.md` | 인프라 미설치 |
+| **Model size growth** (hidden ≥ 1024 / layers ≥ 6) | `docs/plans/archive/model_size_experiment.md` | 인프라 미설치 |
 | **Option B** (per-worker interleaved traversal) | plan 미작성 | 미시작 |
 | **AMP** trainer | `docs/plans/archive/amp_trainer.md` (구현 됨, default off) | 모델 키운 후 재측정 |
-| **torch.compile** trainer | `docs/plans/torch_compile.md` | 모델 키운 후 재측정 |
+| **torch.compile** trainer | `docs/plans/archive/torch_compile.md` | 모델 키운 후 재측정 |
 | **TensorRT** inference | plan 미작성 | 모델 키운 + eval dense 시점 |
 | **Option A re-enable** | 코드 있음 (default off) | 모델 키운 후 또는 Option B 후 |
 | **Julia port** | `docs/research/julia_port_evaluation.md` | Torch.jl 결과 대기 중. Flux FAIL. |
diff --git a/docs/research/option-a-bench-result.md b/docs/research/option-a-bench-result.md
index cf6a098..bcd0f1b 100644
--- a/docs/research/option-a-bench-result.md
+++ b/docs/research/option-a-bench-result.md
@@ -19,7 +19,7 @@ with torch.inference_mode():
     advantages = networks[player](x).squeeze(0).detach().cpu().numpy().astype(np.float32)
 ```
 
-When `traversal.inference_backend` is set to `server` in `configs/deep_cfr/default.yaml`, the `networks[player]` call is intercepted by a `NetworkProxy` (instantiated in `workers.py`, around line 91). This proxy posts a request to the `InferenceServer` and blocks until a response is received via a per-slot event.
+When `traversal.inference_backend` is set to `server` in `legacy/deep-cfr/configs/default.yaml`, the `networks[player]` call is intercepted by a `NetworkProxy` (instantiated in `workers.py`, around line 91). This proxy posts a request to the `InferenceServer` and blocks until a response is received via a per-slot event.
 
 The server's batching logic in `src/coolrl_lost_cities/games/classic/deep_cfr/inference_server.py` (around line 221) reports the realized batch size:
 
@@ -46,7 +46,7 @@ The "structural ceiling" is that `batch_window_us` and `max_batch` tuning cannot
 
 ## Practical implication
 
-Option A is deferred for the current small MLP models (512x3). The `local` backend remains the default in `configs/deep_cfr/default.yaml`.
+Option A is deferred for the current small MLP models (512x3). The `local` backend remains the default in `legacy/deep-cfr/configs/default.yaml`.
 
 To unlock the projected GPU gains, the traversal must be restructured to drive batch sizes up. This leads to two primary paths:
 1.  **Option B (Interleaved Traversal):** Refactor the Cython traversal into a state machine that can advance multiple traversals concurrently per worker. Each worker would suspend at a policy call, batch its own requests, and resume continuations once the results return.
diff --git a/docs/research/post-a-optimization-calculus.md b/docs/research/post-a-optimization-calculus.md
index 410aa46..5b9f905 100644
--- a/docs/research/post-a-optimization-calculus.md
+++ b/docs/research/post-a-optimization-calculus.md
@@ -9,7 +9,7 @@ Why do architectural optimizations like `torch.compile` and TensorRT integration
 
 ## Code reference
 
-The current baseline configuration is defined in `configs/deep_cfr/default.yaml`:
+The historical baseline configuration is defined in `legacy/deep-cfr/configs/default.yaml`:
 
 ```yaml
 network:
@@ -51,4 +51,4 @@ Avoid premature optimization with `torch.compile` or TensorRT on the current sma
 
 - `docs/archive/deep-cfr-performance-experiments-2026-05-07.md` (Small-model regression data)
 - `docs/archive/option-a-bench-result-2026-05-07.md` (Batched traversal benchmarks)
-- `docs/performance.md` (Current runtime bottleneck profile)
\ No newline at end of file
+- `docs/performance.md` (Current runtime bottleneck profile)
diff --git a/docs/research/strategy-memory-location.md b/docs/research/strategy-memory-location.md
index 600ad75..dffa34a 100644
--- a/docs/research/strategy-memory-location.md
+++ b/docs/research/strategy-memory-location.md
@@ -46,7 +46,7 @@ sampling-mode branch. The `info_state` is computed by `_policy(state,
 player, ...)` for the *current acting player*, which is the right thing in
 both conventions.
 
-`configs/deep_cfr/default.yaml` sets:
+`legacy/deep-cfr/configs/default.yaml` sets:
 
 ```yaml
 store_strategy_on_traverser_nodes: true
diff --git a/experiments/option_b_interleaved_traversal/README.md b/experiments/option_b_interleaved_traversal/README.md
index 911e6af..7a70efb 100644
--- a/experiments/option_b_interleaved_traversal/README.md
+++ b/experiments/option_b_interleaved_traversal/README.md
@@ -1,6 +1,6 @@
 # Option B Interleaved Traversal Prototype
 
-Experiment-only prototype for `docs/plans/option_b_interleaved_traversal.md`.
+Experiment-only prototype for `docs/plans/archive/option_b_interleaved_traversal.md`.
 It does not wire into the trainer and does not replace the production Cython
 recursive traversal path.
 
@@ -37,7 +37,7 @@ uv run python experiments/option_b_interleaved_traversal/prototype_interleaved.p
   --output experiments/option_b_interleaved_traversal/results_cuda.json
 ```
 
-2026-05-07 results, `configs/deep_cfr/default.yaml`, RTX 3090 host:
+2026-05-07 results, `legacy/deep-cfr/configs/default.yaml`, RTX 3090 host:
 
 | Device | Mode | total s | forward s | scheduler s | batch mean | batch max | speedup |
 | --- | --- | ---: | ---: | ---: | ---: | ---: | ---: |
diff --git a/experiments/option_b_interleaved_traversal/prototype_interleaved.py b/experiments/option_b_interleaved_traversal/prototype_interleaved.py
index 303fad3..d2e5ff6 100644
--- a/experiments/option_b_interleaved_traversal/prototype_interleaved.py
+++ b/experiments/option_b_interleaved_traversal/prototype_interleaved.py
@@ -650,7 +650,7 @@ def _build_proto_config(cfg: Any, max_depth: int | None, max_nodes: int | None)
 
 def main() -> None:
     parser = argparse.ArgumentParser()
-    parser.add_argument("--config", default="configs/deep_cfr/default.yaml")
+    parser.add_argument("--config", default="legacy/deep-cfr/configs/default.yaml")
     parser.add_argument("--device", default="cpu")
     parser.add_argument("--traversals", type=int, default=64)
     parser.add_argument("--interleave-width", type=int, default=32)
diff --git a/experiments/traversal_policy_boundary/README.md b/experiments/traversal_policy_boundary/README.md
index 960c68c..09d803c 100644
--- a/experiments/traversal_policy_boundary/README.md
+++ b/experiments/traversal_policy_boundary/README.md
@@ -30,7 +30,7 @@ uv run python experiments/traversal_policy_boundary/bench_policy_boundary.py \
   --output experiments/traversal_policy_boundary/results_cuda.json
 ```
 
-2026-05-07 results, `configs/deep_cfr/default.yaml`, RTX 3090 host:
+2026-05-07 results, `legacy/deep-cfr/configs/default.yaml`, RTX 3090 host:
 
 | Device | Component | Median us/call | p95 us/call |
 | --- | --- | ---: | ---: |
diff --git a/experiments/traversal_policy_boundary/bench_policy_boundary.py b/experiments/traversal_policy_boundary/bench_policy_boundary.py
index 000212f..4a08a5f 100644
--- a/experiments/traversal_policy_boundary/bench_policy_boundary.py
+++ b/experiments/traversal_policy_boundary/bench_policy_boundary.py
@@ -321,7 +321,7 @@ def _print_table(result: dict[str, Any]) -> None:
 
 def main() -> None:
     parser = argparse.ArgumentParser()
-    parser.add_argument("--config", default="configs/deep_cfr/default.yaml")
+    parser.add_argument("--config", default="legacy/deep-cfr/configs/default.yaml")
     parser.add_argument("--device", default="cpu")
     parser.add_argument("--traversals", type=int, default=32)
     parser.add_argument("--runs", type=int, default=5)
diff --git a/legacy/deep-cfr/README.md b/legacy/deep-cfr/README.md
new file mode 100644
index 0000000..7dd726b
--- /dev/null
+++ b/legacy/deep-cfr/README.md
@@ -0,0 +1,4 @@
+# Deep CFR archive
+
+These YAML files are retained only to reproduce historical Deep CFR work. The
+supported training stack is JAX PPO; start with `configs/jax_ppo/` instead.
diff --git a/configs/deep_cfr/default.yaml b/legacy/deep-cfr/configs/default.yaml
similarity index 100%
rename from configs/deep_cfr/default.yaml
rename to legacy/deep-cfr/configs/default.yaml
diff --git a/configs/deep_cfr/default_server.yaml b/legacy/deep-cfr/configs/default_server.yaml
similarity index 100%
rename from configs/deep_cfr/default_server.yaml
rename to legacy/deep-cfr/configs/default_server.yaml
diff --git a/configs/deep_cfr/smoke.yaml b/legacy/deep-cfr/configs/smoke.yaml
similarity index 100%
rename from configs/deep_cfr/smoke.yaml
rename to legacy/deep-cfr/configs/smoke.yaml
diff --git a/legacy/ismcts/README.md b/legacy/ismcts/README.md
new file mode 100644
index 0000000..4590727
--- /dev/null
+++ b/legacy/ismcts/README.md
@@ -0,0 +1,4 @@
+# ISMCTS archive
+
+These YAML files are retained only to reproduce historical ISMCTS work. The
+supported training stack is JAX PPO; start with `configs/jax_ppo/` instead.
diff --git a/scripts/autonomous_cycle_eval.sh b/legacy/ismcts/autonomous_cycle_eval.sh
similarity index 84%
rename from scripts/autonomous_cycle_eval.sh
rename to legacy/ismcts/autonomous_cycle_eval.sh
index 31c2e9c..d8f8870 100755
--- a/scripts/autonomous_cycle_eval.sh
+++ b/legacy/ismcts/autonomous_cycle_eval.sh
@@ -27,4 +27,5 @@ if [ ! -f "$CKPT" ]; then
 fi
 
 echo "=== eval $CKPT ==="
-uv run lost-cities-ismcts eval --ckpt "$CKPT" --games 30 --verbose "$@" 2>&1
+uv run python -m coolrl_lost_cities.games.classic.ismcts.cli \
+    eval --ckpt "$CKPT" --games 30 --verbose "$@" 2>&1
diff --git a/configs/ismcts/default.yaml b/legacy/ismcts/configs/default.yaml
similarity index 100%
rename from configs/ismcts/default.yaml
rename to legacy/ismcts/configs/default.yaml
diff --git a/configs/ismcts/mini.yaml b/legacy/ismcts/configs/mini.yaml
similarity index 100%
rename from configs/ismcts/mini.yaml
rename to legacy/ismcts/configs/mini.yaml
diff --git a/pyproject.toml b/pyproject.toml
index 83639e4..fc07f56 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,7 +1,7 @@
 [project]
 name = "coolrl-lost-cities"
 version = "0.1.0"
-description = "Focused Lost Cities classic game extraction"
+description = "JAX PPO training and browser play for Lost Cities"
 readme = "README.md"
 authors = [
     { name = "정시원", email = "sebastianrcnt@gmail.com" }
@@ -34,8 +34,6 @@ lost-cities-classic = "coolrl_lost_cities.games.classic:main"
 lost-cities-eval = "coolrl_lost_cities.games.classic.evaluation:main"
 lost-cities-classic-gui = "coolrl_lost_cities.games.classic.pygame_pvp:main"
 lost-cities-play = "coolrl_lost_cities.games.classic.pygame_table:main"
-lost-cities-deep-cfr = "coolrl_lost_cities.games.classic.deep_cfr.cli:main"
-lost-cities-ismcts = "coolrl_lost_cities.games.classic.ismcts.cli:main"
 lost-cities-jax-ppo = "lost_cities_jax.ppo_cli:main"
 
 [dependency-groups]
diff --git a/scripts/bench_inference_backend.py b/scripts/bench_inference_backend.py
index ef7efd3..d934088 100644
--- a/scripts/bench_inference_backend.py
+++ b/scripts/bench_inference_backend.py
@@ -37,12 +37,12 @@ def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(description="Benchmark Deep CFR traversal inference backends.")
     parser.add_argument(
         "--config-local",
-        default="configs/deep_cfr/default.yaml",
+        default="legacy/deep-cfr/configs/default.yaml",
         help="Config for the local traversal inference backend.",
     )
     parser.add_argument(
         "--config-server",
-        default="configs/deep_cfr/default_server.yaml",
+        default="legacy/deep-cfr/configs/default_server.yaml",
         help="Config for the server traversal inference backend.",
     )
     parser.add_argument("--iterations", type=int, default=10)
diff --git a/scripts/export_jax_ppo_onnx.py b/scripts/export_jax_ppo_onnx.py
index bd8ac44..d5f249e 100644
--- a/scripts/export_jax_ppo_onnx.py
+++ b/scripts/export_jax_ppo_onnx.py
@@ -4,6 +4,7 @@
 from __future__ import annotations
 
 import argparse
+import hashlib
 import json
 from pathlib import Path
 
@@ -86,10 +87,14 @@ def export_model(checkpoint: Path, config: Path | None, output: Path) -> None:
     )
     output.parent.mkdir(parents=True, exist_ok=True)
     onnx.save(model, output)
+    model_bytes = output.read_bytes()
     manifest = {
         "format": "coolrl-lost-cities-jax-ppo-onnx-v1",
-        "source_checkpoint": str(checkpoint.resolve()),
-        "source_config": str(config_path.resolve()),
+        "model_file": output.name,
+        "model_size_bytes": len(model_bytes),
+        "model_sha256": hashlib.sha256(model_bytes).hexdigest(),
+        "source_checkpoint": checkpoint.name,
+        "source_config": config_path.name,
         "observation_size": OBS_DIM,
         "action_size": N_ACTIONS,
         "hidden_size": cfg.network.hidden_size,
diff --git a/scripts/librarian-ignore.txt b/scripts/librarian-ignore.txt
index 28c464c..7117e33 100644
--- a/scripts/librarian-ignore.txt
+++ b/scripts/librarian-ignore.txt
@@ -7,14 +7,7 @@
 #
 # Format examples:
 #   scripts/foo.sh                   # exact path
-#   configs/deep_cfr/model-*.yaml    # glob
+#   configs/jax_ppo/model-*.yaml     # glob
 #   docs/research/*.md               # whole directory
 #
 # Comments after `#` are stripped per line. Blank lines ignored.
-
-# Future config + script described in docs/plans/model_size_experiment.md
-configs/deep_cfr/model-size-*.yaml
-scripts/run_model_size_experiment.sh
-
-# Future config described in docs/plans/torch_compile.md
-configs/deep_cfr/default_compile.yaml
diff --git a/scripts/profile_gpu_forward.py b/scripts/profile_gpu_forward.py
index 83ecd9b..adc29ef 100644
--- a/scripts/profile_gpu_forward.py
+++ b/scripts/profile_gpu_forward.py
@@ -1,7 +1,7 @@
 """Profile GPU forward-pass throughput for the Deep CFR trainer network.
 
 Builds the same DeepCFRMLP that ``DeepCFRTrainer.__init__`` constructs from
-``configs/deep_cfr/default.yaml``, then measures average forward-pass time on
+``legacy/deep-cfr/configs/default.yaml``, then measures average forward-pass time on
 CUDA across a sweep of batch sizes. The goal is to decide whether batched
 traversal inference (Optimization Priorities #5) is worth implementing.
 """
@@ -19,7 +19,7 @@ from coolrl_lost_cities.games.classic.deep_cfr.config import load_config
 from coolrl_lost_cities.games.classic.deep_cfr.networks import DeepCFRMLP
 
 REPO_ROOT = Path(__file__).resolve().parent.parent
-CONFIG_PATH = REPO_ROOT / "configs" / "deep_cfr" / "default.yaml"
+CONFIG_PATH = REPO_ROOT / "legacy" / "deep-cfr" / "configs" / "default.yaml"
 
 BATCH_SIZES = [1, 4, 16, 64, 256, 1024]
 WARMUP_ITERS = 10
diff --git a/src/coolrl_lost_cities/games/classic/ismcts/eval_checkpoint.py b/src/coolrl_lost_cities/games/classic/ismcts/eval_checkpoint.py
index feea2ab..da372e0 100644
--- a/src/coolrl_lost_cities/games/classic/ismcts/eval_checkpoint.py
+++ b/src/coolrl_lost_cities/games/classic/ismcts/eval_checkpoint.py
@@ -6,7 +6,7 @@ against opponents that are not in `evaluation.opponents` (e.g. heuristic-balance
 the rollout policy) and for running many more games than per-iter eval typically
 allows.
 
-Invoked via ``lost-cities-ismcts eval`` (see ``cli.py``).
+Available through the archived ISMCTS CLI module (see ``cli.py``).
 """
 
 from __future__ import annotations
diff --git a/src/coolrl_lost_cities/games/classic/ismcts/pretrain.py b/src/coolrl_lost_cities/games/classic/ismcts/pretrain.py
index 2fccedf..fd82eef 100644
--- a/src/coolrl_lost_cities/games/classic/ismcts/pretrain.py
+++ b/src/coolrl_lost_cities/games/classic/ismcts/pretrain.py
@@ -8,14 +8,12 @@ AlphaZero-style network's policy + value heads in supervised fashion:
 - value loss: MSE on the final game score diff from each decision-maker's
   perspective, normalized by value_scale (same convention as the trainer).
 
-The resulting checkpoint can be passed to `lost-cities-ismcts train
---resume-from` to start self-play with a heuristic-level prior instead of a
-random init. This addresses the self-play "weak-equilibrium" problem: starting
-from random, MCTS visit distributions converge to a mutually mediocre policy
-that has near-zero win rate against the heuristic. Warm-starting at heuristic
-level gives self-play a meaningful baseline to improve from.
-
-Invoked via ``lost-cities-ismcts pretrain``.
+The resulting checkpoint can be passed to the archived ISMCTS trainer to start
+self-play with a heuristic-level prior instead of a random init. This addresses
+the self-play "weak-equilibrium" problem: starting from random, MCTS visit
+distributions converge to a mutually mediocre policy that has near-zero win
+rate against the heuristic. Warm-starting at heuristic level gives self-play a
+meaningful baseline to improve from.
 """
 
 from __future__ import annotations
diff --git a/tests/games/classic/test_deep_cfr_trainer.py b/tests/games/classic/test_deep_cfr_trainer.py
index e7450d1..82b77ac 100644
--- a/tests/games/classic/test_deep_cfr_trainer.py
+++ b/tests/games/classic/test_deep_cfr_trainer.py
@@ -44,7 +44,7 @@ def _deep_cfr_config(data: dict) -> DeepCFRConfig:
 
 
 def test_deep_cfr_loads_smoke_yaml_config() -> None:
-    config = load_config("configs/deep_cfr/smoke.yaml")
+    config = load_config("legacy/deep-cfr/configs/smoke.yaml")
 
     assert config.run.max_iterations == 1
     assert config.network.hidden_size == 16
diff --git a/web/README.md b/web/README.md
index 2ba598f..8751838 100644
--- a/web/README.md
+++ b/web/README.md
@@ -1,11 +1,38 @@
 # COOLRL Lost Cities Web
 
 Browser-only Lost Cities client. The rules engine, observation builder, and PPO
-inference all run on the device. There is no application server.
+inference all run on the device; there is no application server.
+
+The verified final JAX PPO policy is committed at
+`public/models/jax-ppo.onnx` (3.1 MB). Vite copies it to the static build, and
+the app resolves the asset relative to the deployed site so it works on GitHub
+Pages, GitLab Pages, or a normal web root. Its size and SHA-256 are recorded in
+[`public/models/jax-ppo.json`](public/models/jax-ppo.json).
+
+Pushes to `main` build and publish the client through the repository's GitHub
+Pages and GitLab Pages workflows. Each workflow supplies the correct base URL
+for its host.
 
 ## Setup
 
-From the repository root, export an Orbax checkpoint to the browser model:
+Install and run the checked-in final policy:
+
+```bash
+cd web
+npm ci
+npm run dev
+```
+
+Build the same static bundle used by a host:
+
+```bash
+npm run build
+npm run preview
+```
+
+To replace the shipped policy, export a verified Orbax checkpoint from the
+repository root. The exporter writes both the ONNX file and its public
+metadata manifest:
 
 ```bash
 uv run --with onnx scripts/export_jax_ppo_onnx.py \
@@ -13,14 +40,6 @@ uv run --with onnx scripts/export_jax_ppo_onnx.py \
   --output web/public/models/jax-ppo.onnx
 ```
 
-Then install and run the web app:
-
-```bash
-cd web
-npm install
-npm run dev
-```
-
 The policy tries WebGPU first and falls back to ONNX Runtime WebAssembly. If
 the model asset is absent, the UI remains playable using a simple local
 heuristic and reports that fallback in the header.
diff --git a/web/public/models/jax-ppo.json b/web/public/models/jax-ppo.json
new file mode 100644
index 0000000..9ccec5b
--- /dev/null
+++ b/web/public/models/jax-ppo.json
@@ -0,0 +1,14 @@
+{
+  "format": "coolrl-lost-cities-jax-ppo-onnx-v1",
+  "model_file": "jax-ppo.onnx",
+  "model_size_bytes": 3230780,
+  "model_sha256": "e8241e305c01ea450e92a6178002a22db96710fa94e238bba57953743eb285b2",
+  "source_checkpoint": "final_candidate",
+  "source_config": "main_ppo_config.json",
+  "observation_size": 454,
+  "action_size": 96,
+  "hidden_size": 512,
+  "num_layers": 3,
+  "dtype": "float32",
+  "validation_max_abs_error": 9.918212890625e-05
+}
diff --git a/web/public/models/jax-ppo.onnx b/web/public/models/jax-ppo.onnx
new file mode 100644
index 0000000..630b5a1
Binary files /dev/null and b/web/public/models/jax-ppo.onnx differ
diff --git a/web/src/model/policy.ts b/web/src/model/policy.ts
index 85bbfdc..291d3c2 100644
--- a/web/src/model/policy.ts
+++ b/web/src/model/policy.ts
@@ -7,6 +7,8 @@ import { cardColor, cardRank, isHandshake } from "../game/cards";
 
 export type ExecutionProvider = "webgpu" | "wasm" | "heuristic";
 
+const MODEL_URL = `${import.meta.env.BASE_URL}models/jax-ppo.onnx`;
+
 export interface Policy {
   readonly provider: ExecutionProvider;
   action(state: GameState): Promise<number>;
@@ -66,7 +68,7 @@ class HeuristicPolicy implements Policy {
 }
 
 async function createSession(provider: "webgpu" | "wasm"): Promise<ort.InferenceSession> {
-  return ort.InferenceSession.create("/models/jax-ppo.onnx", {
+  return ort.InferenceSession.create(MODEL_URL, {
     executionProviders: [provider],
     graphOptimizationLevel: "all",
   });