feat(webmd_doctor): add WebMD Doctor mirror (site 25, port 40024)

.assets-revision

@@ -5,4 +5,4 @@
 # is a git revision (branch name like `main`, a tag, or a specific commit
 # sha). Override at runtime with the ASSETS_REVISION env var.
 repo: ChilleD/WebHarbor
-revision: 68dcbf2cbd0cbc2fbf97dcb71da13ace67c11bf6
+revision: ad6f424f72cada9e6f5c09a58093d0ceeab9c52b

.claude/skills/clone-website/SKILL.md

@@ -204,7 +204,7 @@ Then run the site once locally to produce `instance/<site>.db`, copy it to
 ```bash
 ./scripts/build.sh webharbor:dev
 docker run -d --rm --name wh-test \
-  -p 8201:8101 -p 41000-41024:40000-40024 webharbor:dev
+  -p 8201:8101 -p 41000-41025:40000-40025 webharbor:dev
 
 # your new site is on port 41000 + its index
 curl -so /dev/null -w "%{http_code}\n" http://localhost:41000NN/
@@ -228,7 +228,7 @@ After Phase 1, you should have:
 - `sites/<your_site>/static/` with real CSS/JS/icons (and images under HF assets)
 - `sites/<your_site>/instance_seed/<site>.db` with seeded data
 - Site registered in `websyn_start.sh`, `control_server.py`, `Dockerfile`
-- All 25 sites still return 200 on the alt-port container
+- All 26 sites still return 200 on the alt-port container
 - Byte-identical reset passes
 
 ## Next step

.claude/skills/evolve-env/SKILL.md

@@ -65,15 +65,15 @@ through `BASE_DIR = os.path.dirname(os.path.abspath(__file__))`.
 After any DB-affecting change:
 
 ```bash
-# 1. Stop test container (don't touch user's working container on :40000-40024)
+# 1. Stop test container (don't touch user's working container on :40000-40025)
 docker stop wh-test 2>/dev/null || true
 
 # 2. Rebuild
 ./scripts/build.sh webharbor:dev
 
 # 3. Run on alt ports
 docker run -d --rm --name wh-test \
-  -p 8201:8101 -p 41000-41024:40000-40024 webharbor:dev
+  -p 8201:8101 -p 41000-41025:40000-40025 webharbor:dev
 
 # 4. Reset your site and confirm byte-identity
 curl -X POST http://localhost:8201/reset/<your_site>
@@ -149,7 +149,7 @@ After Phase 3:
 - Every task in `tasks.jsonl` is hand-verified to work end-to-end
 - The mirror has no obvious leaks, broken forms, or empty pages
 - Byte-identical reset passes
-- All 25 sites still return 200
+- All 26 sites still return 200
 
 ## Next step
 

.claude/skills/harden-env/SKILL.md

@@ -130,7 +130,7 @@ Hardening changes seed data. After any DB change:
 ```bash
 ./scripts/build.sh webharbor:dev
 docker run -d --rm --name wh-test \
-  -p 8201:8101 -p 41000-41024:40000-40024 webharbor:dev
+  -p 8201:8101 -p 41000-41025:40000-40025 webharbor:dev
 curl -X POST http://localhost:8201/reset/<your_site>
 docker exec wh-test md5sum \
   /opt/WebSyn/<your_site>/instance/<your_site>.db \

.claude/skills/review-env/SKILL.md

@@ -33,18 +33,18 @@ gh pr checkout <pr-number>
 ./scripts/fetch_assets.sh             # pull the pinned HF revision
 ./scripts/build.sh webharbor:dev
 docker run -d --rm --name wh-review \
-  -p 8201:8101 -p 41000-41024:40000-40024 webharbor:dev
+  -p 8201:8101 -p 41000-41025:40000-40025 webharbor:dev
 ```
 
-Confirm the new/changed site is on the expected port (40000 + index). Note: the image now runs 25 sites (40000-40024).
+Confirm the new/changed site is on the expected port (40000 + index). Note: the image now runs 26 sites (40000-40025).
 
 ### Step 2: The mechanical checks (5 minutes)
 
 Run the same Pre-PR checks the contributor was supposed to run.
 
 ```bash
-# 1. all 25 sites return 200
-for p in $(seq 41000 41024); do
+# 1. all 26 sites return 200
+for p in $(seq 41000 41025); do
   curl -so /dev/null -w "$p:%{http_code}\n" http://localhost:$p/
 done
 
@@ -231,7 +231,7 @@ Leave a structured comment on the PR:
 ## Review: <site_name>
 
 ### Mechanical checks: PASS / FAIL
-- [x] All 25 sites return 200
+- [x] All 26 sites return 200
 - [x] Control plane healthy
 - [x] Byte-identical reset (md5 match)
 - [x] Parallel reset <10s

.claude/skills/seed-database/SKILL.md

@@ -169,10 +169,10 @@ gh pr create
 ./scripts/check_assets.sh                       # every site has instance_seed/
 ./scripts/build.sh webharbor:dev                # docker build succeeds
 docker run -d --rm --name wh-test \
-  -p 8201:8101 -p 41000-41024:40000-40024 webharbor:dev
+  -p 8201:8101 -p 41000-41025:40000-40025 webharbor:dev
 
-# all 25 sites return 200
-for p in $(seq 41000 41024); do
+# all 26 sites return 200
+for p in $(seq 41000 41025); do
   curl -so /dev/null -w "$p:%{http_code}\n" http://localhost:$p/
 done
 

AGENTS.md

@@ -48,17 +48,17 @@ Inside the image, sites live at `/opt/WebSyn/<site>/`. The path predates the ren
 # fresh clone
 ./scripts/fetch_assets.sh                     # pulls assets from HF
 ./scripts/build.sh                            # docker build -t webharbor:dev .
-docker run -d -p 8101:8101 -p 40000-40024:40000-40024 webharbor:dev
+docker run -d -p 8101:8101 -p 40000-40025:40000-40025 webharbor:dev
 ```
 
 Or use the published image directly:
 
 ```bash
-docker run -d -p 8101:8101 -p 40000-40024:40000-40024 \
+docker run -d -p 8101:8101 -p 40000-40025:40000-40025 \
   battalion7244/webharbor:latest
 ```
 
-Sites are on `40000`-`40024` in the order declared by `SITES=( ... )` in `websyn_start.sh`. Control plane:
+Sites are on `40000`-`40025` in the order declared by `SITES=( ... )` in `websyn_start.sh`. Control plane:
 
 | Method | Path                | Purpose                                   |
 |--------|---------------------|-------------------------------------------|
@@ -136,13 +136,13 @@ python3 -m py_compile sites/<site>/app.py
 
 # 3. run on alt ports (don't collide with anything you already have running)
 docker run -d --rm --name wh-test \
-  -p 8201:8101 -p 41000-41024:40000-40024 webharbor:dev
+  -p 8201:8101 -p 41000-41025:40000-40025 webharbor:dev
 
 # 4. control plane healthy, all sites alive
 curl -s http://localhost:8201/health | python3 -m json.tool | head
 
 # 5. every site renders 200
-for p in $(seq 41000 41024); do
+for p in $(seq 41000 41025); do
   curl -so /dev/null -w "$p:%{http_code}\n" http://localhost:$p/
 done
 

CLAUDE.md

@@ -16,4 +16,4 @@ The full agent guide is loaded above via `@AGENTS.md`. The notes below apply onl
 
 ## Existing containers
 
-If a container is already running on `:8101` / `:40000-40024`, treat it as the user's working environment — don't `docker stop` or `docker rm` it without explicit confirmation. Spin up your test container under a different name on alt ports (`:8201`, `:41000-41024`).
+If a container is already running on `:8101` / `:40000-40025`, treat it as the user's working environment — don't `docker stop` or `docker rm` it without explicit confirmation. Spin up your test container under a different name on alt ports (`:8201`, `:41000-41025`).

CONTRIBUTING.md

@@ -24,7 +24,7 @@ git clone https://github.com/<you>/webharbor && cd webharbor
 ./scripts/fetch_assets.sh                       # pull current assets
 ./scripts/new_site.py mywebsite                 # OR edit an existing site
 ./scripts/build.sh && docker run -d --rm \
-  -p 8101:8101 -p 40000-40024:40000-40024 webharbor:dev
+  -p 8101:8101 -p 40000-40025:40000-40025 webharbor:dev
 # iterate locally...
 
 ./scripts/extract_assets.sh ../webharbor-static-pr/   # split assets out

Dockerfile

@@ -1,5 +1,5 @@
 # WebHarbor — slim, self-contained image.
-# 25 Flask mirror sites + control plane on :8101.
+# 26 Flask mirror sites + control plane on :8101.
 
 FROM python:3.12-slim-bookworm
 
@@ -56,6 +56,14 @@ RUN python3 /opt/check_asset_inventory.py /opt/WebSyn/fedex
 RUN cd /opt/WebSyn/fedex && rm -rf instance instance_seed && \
     PYTHONHASHSEED=0 python seed_data.py && rm -rf instance
 
+# WebMD Doctor's generated avatars / posters come from the pinned asset bundle,
+# while its SQLite seed is rebuilt deterministically from tracked source code.
+# The inventory gate enforces exact coverage + per-file SHA-256 + PNG decode of
+# all 317 generated images (same contract as the compass / walmart inventories).
+RUN python3 /opt/WebSyn/webmd_doctor/check_generated_assets.py
+RUN cd /opt/WebSyn/webmd_doctor && rm -rf instance instance_seed && \
+    PYTHONHASHSEED=0 python seed_data.py && rm -rf instance __pycache__
+
 COPY websyn_start.sh    /opt/websyn_start.sh
 COPY control_server.py  /opt/control_server.py
 COPY site_runner.py     /opt/site_runner.py
@@ -78,6 +86,6 @@ os.makedirs('instance_seed', exist_ok=True); \
 shutil.copy2('instance/rotten_tomatoes.db', 'instance_seed/rotten_tomatoes.db'); \
 print('Rotten Tomatoes seed DB generated at build time.')" && rm -rf /opt/WebSyn/rotten_tomatoes/instance
 
-EXPOSE 8101 40000-40024
+EXPOSE 8101 40000-40025
 
 CMD ["/opt/websyn_start.sh"]

README.md

@@ -36,17 +36,17 @@ WebHarbor takes a different approach. We leverage coding agent (e.g., Claude Cod
 - **Deep features unlocked** — carts, checkouts, accounts, all fully testable
 - **Evolving** — harder tasks drive richer mirrors; the environment grows with agents
 - **RL-ready** — sub-second database resets between rollouts
-- **Community-driven** — 25 sites today, scaling to 100+ together
+- **Community-driven** — 26 sites today, scaling to 100+ together
 
 ## 🚀 Quickstart
 
 One command to run all web environments:
 
 ```bash
-docker run -p 8101:8101 -p 40000-40024:40000-40024 battalion7244/webharbor:latest
+docker run -p 8101:8101 -p 40000-40025:40000-40025 battalion7244/webharbor:latest
 ```
 
-Then point your agent at `http://localhost:40000` through `http://localhost:40024` to explore 25 local mirrors of WebVoyager sites: `Allrecipes, Amazon, Apple, ArXiv, BBC News, Booking, GitHub, Google Flights, Google Maps, Google Search, Hugging Face, Wolfram Alpha, Cambridge Dictionary, Coursera, ESPN, Merriam-Webster, IKEA, Phys.org, Target, TED, Ohio State University, Rotten Tomatoes, Compass, Walmart Careers, and FedEx`.
+Then point your agent at `http://localhost:40000` through `http://localhost:40025` to explore 26 local mirrors of WebVoyager sites: `Allrecipes, Amazon, Apple, ArXiv, BBC News, Booking, GitHub, Google Flights, Google Maps, Google Search, Hugging Face, Wolfram Alpha, Cambridge Dictionary, Coursera, ESPN, Merriam-Webster, IKEA, Phys.org, Target, TED, Ohio State University, Rotten Tomatoes, Compass, Walmart Careers, FedEx, and WebMD Doctor`.
 
 For sub-second reset between rollouts, expose the control plane and call `/reset/<site>`:
 

agent_demo/README.md

@@ -19,7 +19,7 @@ export OPENAI_BASE_URL=https://api.openai.com/v1   # or your Azure / vLLM endpoi
 
 ## Run a task
 
-WebHarbor must already be running locally (`docker run -p 8101:8101 -p 40000-40024:40000-40024 battalion7244/webharbor:latest`).
+WebHarbor must already be running locally (`docker run -p 8101:8101 -p 40000-40025:40000-40025 battalion7244/webharbor:latest`).
 
 Run a single task from a site's `tasks.jsonl`:
 

control_server.py

@@ -28,6 +28,7 @@
     'huggingface', 'wolfram_alpha', 'cambridge_dictionary',
     'coursera', 'espn', 'merriam_webster', 'ikea', 'phys_org', 'target',
     'ted', 'osu', 'rotten_tomatoes', 'compass', 'walmart_careers', 'fedex',
+    'webmd_doctor',
 ]
 BASE_PORT = 40000
 WEBSYN_DIR = '/opt/WebSyn'

scripts/check_assets.sh

@@ -37,6 +37,9 @@ for site in sites/*/; do
     if [[ -f "sites/$s/asset_inventory.json" ]]; then
         python3 scripts/check_asset_inventory.py "sites/$s"
     fi
+    if [[ -f "sites/$s/generated_asset_inventory.json" && -f "sites/$s/check_generated_assets.py" ]]; then
+        python3 "sites/$s/check_generated_assets.py"
+    fi
 done
 
 if (( missing > 0 )); then

sites/fedex/README.md

@@ -1,6 +1,6 @@
 # FedEx
 
-An offline FedEx mirror contributed in [WebHarbor #50](https://github.com/aiming-lab/WebHarbor/pull/50) and revised in [WebHarbor #82](https://github.com/aiming-lab/WebHarbor/pull/82), with package tracking, rate estimates, a shipping flow, pickup scheduling, a location directory, local support articles, accounts, shipment history, invoices and claims. FedEx uses port **40024** in the current 25-site registry.
+An offline FedEx mirror contributed in [WebHarbor #50](https://github.com/aiming-lab/WebHarbor/pull/50) and revised in [WebHarbor #82](https://github.com/aiming-lab/WebHarbor/pull/82), with package tracking, rate estimates, a shipping flow, pickup scheduling, a location directory, local support articles, accounts, shipment history, invoices and claims. FedEx uses port **40024** in the current 26-site registry.
 
 ## Data and assets
 

sites/rotten_tomatoes/tests/test_environment_quality.py

@@ -94,6 +94,10 @@ def test_task_manifest_and_registry(self):
         sites = re.search(r'SITES=\((.*?)\)', startup, re.S).group(1).split()
         self.assertIn('rotten_tomatoes', sites)
         self.assertEqual(40000 + sites.index('rotten_tomatoes'), 40021)
+        self.assertIn('fedex', sites)
+        self.assertEqual(40000 + sites.index('fedex'), 40024)
+        self.assertIn('webmd_doctor', sites)
+        self.assertEqual(40000 + sites.index('webmd_doctor'), 40025)
         self.assertIn("'ted', 'osu', 'rotten_tomatoes'", (ROOT / 'control_server.py').read_text())
         self.assertIn(f'40000-{40000 + len(sites) - 1}', (ROOT / 'Dockerfile').read_text())
         self.assertTrue((SITE / '.build-generated-seed').is_file())

sites/walmart_careers/README.md

@@ -1,6 +1,6 @@
 # Walmart Careers mirror
 
-This directory contains an offline Flask mirror modeled on `https://careers.walmart.com`. In the 24-site registry it runs on container port `40023`. All jobs, stores, requisition identifiers, user accounts, saved roles and applications are deterministic synthetic benchmark data.
+This directory contains an offline Flask mirror modeled on `https://careers.walmart.com`. In the 26-site registry it runs on container port `40023`. All jobs, stores, requisition identifiers, user accounts, saved roles and applications are deterministic synthetic benchmark data.
 
 ## Runtime
 

sites/walmart_careers/tests/test_integration.py

@@ -16,7 +16,7 @@
     "cambridge_dictionary", "coursera", "espn", "merriam_webster", "ikea", "phys_org",
     "target", "ted", "osu", "rotten_tomatoes", "compass",
 ]
-FIXED_PORTS = {"rotten_tomatoes": 40021, "compass": 40022, "walmart_careers": 40023, "fedex": 40024}
+FIXED_PORTS = {"rotten_tomatoes": 40021, "compass": 40022, "walmart_careers": 40023, "fedex": 40024, "webmd_doctor": 40025}
 
 
 def registered_sites() -> list[str]:
@@ -54,7 +54,7 @@ def control_sites():
 def test_registry_is_consistent_and_preserves_assigned_ports():
     sites = registered_sites()
     assert sites[:len(PREFIX_SITES)] == PREFIX_SITES
-    assert "walmart_careers" in sites and "fedex" in sites
+    assert "walmart_careers" in sites and "fedex" in sites and "webmd_doctor" in sites
     assert len(sites) == len(set(sites)), "duplicate site in the registry"
     for site, port in FIXED_PORTS.items():
         assert site_port(site) == port, f"{site} moved to {site_port(site)}, expected {port}"
@@ -68,6 +68,9 @@ def test_docker_preserves_build_gates_for_every_inventoried_site():
     for site in ("compass", "walmart_careers", "fedex"):
         assert f"check_asset_inventory.py /opt/WebSyn/{site}" in text, site
         assert f"cd /opt/WebSyn/{site}" in text, site
+    # WebMD Doctor ships its own generated-asset gate plus a source-built seed.
+    assert "/opt/WebSyn/webmd_doctor/check_generated_assets.py" in text
+    assert "cd /opt/WebSyn/webmd_doctor" in text
     assert "walmart_careers/check_tracked_assets.py" in text
     for site in ("osu", "rotten_tomatoes"):
         assert f"cd /opt/WebSyn/{site}" in text, site
@@ -85,7 +88,7 @@ def test_tasks_and_verifiers_are_complete_and_use_site_24():
 def test_assets_pin_is_immutable_merged_revision():
     text = (ROOT / ".assets-revision").read_text()
     revision = re.search(r"^revision:\s*([0-9a-f]+)$", text, re.M).group(1)
-    assert revision == "68dcbf2cbd0cbc2fbf97dcb71da13ace67c11bf6"
+    assert revision == "ad6f424f72cada9e6f5c09a58093d0ceeab9c52b"
     assert (SITE / ".build-generated-seed").is_file()
     assert (SITE / ".requires-images").is_file()
     assert (SITE / "asset_inventory.json").is_file()
@@ -94,7 +97,7 @@ def test_assets_pin_is_immutable_merged_revision():
 
 def test_shared_documentation_uses_the_current_site_range():
     current = port_range()
-    stale = {f"40000-400{end}" for end in range(20, 24)} - {current}
+    stale = {f"40000-400{end}" for end in range(20, 25)} - {current}
     for relative in ["README.md", "AGENTS.md", "CONTRIBUTING.md", "CLAUDE.md", "agent_demo/README.md"]:
         text = (ROOT / relative).read_text()
         for old in stale:

sites/webmd_doctor/.build-generated-seed

@@ -0,0 +1 @@
+The Dockerfile generates instance_seed/webmd_doctor.db deterministically from tracked source code (seed_data.py); static/images/ ships from the pinned Hugging Face archive.

sites/webmd_doctor/.gitignore

@@ -0,0 +1,2 @@
+# Local build/inspection helpers (ground truth, assertions, audits): never shipped with the site.
+scripts_dev/

sites/webmd_doctor/.requires-images

@@ -0,0 +1 @@
+WebMD Doctor requires its generated initials avatars and video poster frames (static/images/{avatars,posters}/) from the pinned Hugging Face archive.