Rename web-app/ directory to web/

.github/workflows/python-test.yml

@@ -61,7 +61,7 @@ jobs:
 
       - name: Install Node.js packages
         run: npm ci
-        working-directory: web-app
+        working-directory: web
 
       - name: Install Python packages
         run: uv sync --all-packages

.github/workflows/typescript-lint.yml

@@ -7,23 +7,23 @@ on:
       - production
     paths:
       - .github/workflows/typescript-lint.yml
-      - web-app/**
+      - web/**
       - Makefile
   pull_request:
     branches:
       - staging
       - production
     paths:
       - .github/workflows/typescript-lint.yml
-      - web-app/**
+      - web/**
       - Makefile
 
 jobs:
   typescript-lint:
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: web-app
+        working-directory: web
     steps:
       - uses: actions/checkout@v6
 

.github/workflows/typescript-test.yml

@@ -7,15 +7,15 @@ on:
       - production
     paths:
       - .github/workflows/typescript-test.yml
-      - web-app/**
+      - web/**
       - Makefile
   pull_request:
     branches:
       - staging
       - production
     paths:
       - .github/workflows/typescript-test.yml
-      - web-app/**
+      - web/**
       - Makefile
 
 jobs:
@@ -51,7 +51,7 @@ jobs:
 
       - name: Install packages
         run: npm ci
-        working-directory: web-app
+        working-directory: web
 
       - name: Run MCP tests
         run: make fe-test-mcp

Makefile

@@ -49,35 +49,35 @@ py-check-watcher-version:
 # Web app.
 .PHONY: fe-format
 fe-format:
-	cd web-app && npm run format
+	cd web && npm run format
 
 .PHONY: fe-lint
 fe-lint:
-	cd web-app && npm run lint
+	cd web && npm run lint
 
 .PHONY: fe-typecheck
 fe-typecheck:
-	cd web-app && npm run typecheck
+	cd web && npm run typecheck
 
 .PHONY: fe-test-mcp
 fe-test-mcp:
-	cd web-app && npm run test:mcp
+	cd web && npm run test:mcp
 
 .PHONY: fe-test-integration
 fe-test-integration:
-	cd web-app && npm run test:integration
+	cd web && npm run test:integration
 
 .PHONY: fe-test
 fe-test:
-	cd web-app && npm run test:mcp && npm run test:integration
+	cd web && npm run test:mcp && npm run test:integration
 
 .PHONY: dev
 dev:
-	cd web-app && npm run dev
+	cd web && npm run dev
 
 .PHONY: fe-build
 fe-build:
-	cd web-app && npm run build
+	cd web && npm run build
 
 # Formatting, linting, and type checking.
 .PHONY: py-check

README.md

@@ -16,7 +16,7 @@ flowchart LR
 
 | Directory | Description | Docs |
 | --- | --- | --- |
-| `web-app/` | Next.js web application and REST API (Vercel) | [API reference](docs/api.md) |
+| `web/` | Next.js web application and REST API (Vercel) | [API reference](docs/api.md) |
 | `lambda/` | AWS Lambda function for instrument data processing | [Lambda docs](docs/lambda.md) |
 | `watcher/` | CLI agent for lab instrument PCs | [Watcher docs](docs/watcher.md) |
 | `packages/shared/` | Shared Python library (S3, enums, test infra) | [Shared library](docs/shared-library.md) |
@@ -29,13 +29,13 @@ flowchart LR
 uv sync --all-packages
 
 # Install web app dependencies.
-cd web-app && npm install && cd ..
+cd web && npm install && cd ..
 
 # Set up environment variables for the web app.
-cd web-app && vercel env pull && cd ..
+cd web && vercel env pull && cd ..
 
 # Create and initialize the local database.
-cd web-app && createdb data-hub-local && npm run db:push && cd ..
+cd web && createdb data-hub-local && npm run db:push && cd ..
 
 # Start the dev server.
 make dev

docs/architecture.md

@@ -24,7 +24,7 @@ flowchart LR
 
 | Directory | Package | Description |
 | --- | --- | --- |
-| `web-app/` | `data-hub-web-app` | Next.js web application, REST API, and MCP server. Deployed on Vercel. |
+| `web/` | `data-hub-web` | Next.js web application, REST API, and MCP server. Deployed on Vercel. |
 | `lambda/` | `data-hub-lambda` | AWS Lambda function triggered by S3 uploads. Runs instrument-specific processing pipelines. |
 | `watcher/` | `data-hub-watcher` | CLI agent installed on lab instrument PCs. Detects new files, uploads them to S3, and reports status to the API. |
 | `packages/shared/` | `data-hub-shared` | Shared Python library providing S3 utilities, instrument enums, and test infrastructure. |
@@ -56,7 +56,7 @@ Steps 1–3 are the same, but the watcher does not upload immediately. Instead:
 - **API-driven coordination.** The watcher registers with the API, syncs its YAML config, and sends periodic heartbeats. This lets the web dashboard show watcher health and manage upload queues.
 - **Presigned URLs from the API.** The web app generates presigned S3 upload and download URLs so watchers and browsers can transfer files directly to/from S3 without routing data through the API. On Vercel, the app assumes an IAM role via OIDC federation (no long-lived AWS credentials).
 - **Lambda-built run archives.** The "Download all" actions on a run delegate to the Lambda, which streams files from the raw + processed buckets directly into a zip in a separate `arcadia-data-hub-archives-{env}` bucket via S3 multipart upload. The web app then 302s the browser to a short-lived presigned URL on that archive — bytes never traverse Vercel, eliminating Fast Origin Transfer for run downloads. Builds are cached at `runs/{instrument_id}/{run_id}/{fingerprint}.zip` and expire after 7 days. Every cache miss is dispatched asynchronously: the route inserts an `archive_jobs` row, schedules the Lambda invocation via `after()`, returns `202 { job_id }`, and the UI polls the same `/download-archive` URL (which HEADs S3 on each call) until the artifact appears — making the S3 object, not the row's `status`, the source of truth for "ready". See [Run archives](run-archives.md) for the full flow and runbook.
-- **Public page metadata, gated bodies.** Routes commonly shared into Slack/Notion (dashboard, instruments, instrument and run detail, settings) are reachable without a session so link unfurlers can read `<head>` metadata; the page or layout renders a `SignInRequired` CTA in place of the real body when there's no session. `/watchers/*` stays redirected to `/login` by `web-app/proxy.ts`. Three independent layers prevent search indexing: a `robots` field on the root layout, an `app/robots.ts` that disallows all generic crawlers (with an allow-list for unfurl bots), and an `X-Robots-Tag: noindex, nofollow` header on every response.
+- **Public page metadata, gated bodies.** Routes commonly shared into Slack/Notion (dashboard, instruments, instrument and run detail, settings) are reachable without a session so link unfurlers can read `<head>` metadata; the page or layout renders a `SignInRequired` CTA in place of the real body when there's no session. `/watchers/*` stays redirected to `/login` by `web/proxy.ts`. Three independent layers prevent search indexing: a `robots` field on the root layout, an `app/robots.ts` that disallows all generic crawlers (with an allow-list for unfurl bots), and an `X-Robots-Tag: noindex, nofollow` header on every response.
 - **Shared library for contracts.** Instrument IDs, S3 utilities, and environment config live in `data-hub-shared` so they stay consistent across Lambda and the watcher without duplicating code.
 - **MCP for AI access.** The web app includes a [Model Context Protocol](https://modelcontextprotocol.io/) server at `/api/v1/mcp` that exposes read-only tools, resources, and prompts. AI clients (e.g. Claude Desktop, Cursor) can query instruments, runs, and system status using a personal access token.
 - **Integration tests against a real server.** The shared `testing.py` module spins up a real Next.js server backed by a Postgres database, so Lambda and watcher integration tests exercise the actual API surface.

docs/ci-and-deployment.md

@@ -57,7 +57,7 @@ The Next.js app is deployed on [Vercel](https://vercel.com/arcadia-science/data-
 Environment variables are managed in the Vercel dashboard and can be pulled locally with:
 
 ```sh
-cd web-app
+cd web
 vercel env pull
 ```
 
@@ -68,7 +68,7 @@ Staging and production each have a dedicated PostgreSQL instance hosted on [Rend
 Schema changes are applied with Drizzle:
 
 ```sh
-cd web-app
+cd web
 
 # Generate migration files from schema changes.
 npm run db:generate
@@ -168,7 +168,7 @@ In your GitHub repo, go to **Settings → Environments**, create a `staging` env
 | `DATA_HUB_API_URL` | Base API URL for the environment |
 | `DATA_HUB_API_KEY` | API key for Lambda → Data Hub authentication (also used by the Lambda's archive-job PATCH callback) |
 
-Slack notifications are sent by the **web app** (not the Lambda) when a new run is created. Configure `SLACK_WEBHOOK_URL` per environment in the Vercel dashboard alongside the other web-app env vars listed below.
+Slack notifications are sent by the **web app** (not the Lambda) when a new run is created. Configure `SLACK_WEBHOOK_URL` per environment in the Vercel dashboard alongside the other web app env vars listed below.
 
 You'll also need the `WebAppRoleArn` and `DataHubFunctionUrl` stack outputs to configure the Vercel web app. In the Vercel dashboard (under the appropriate environment), set:
 

docs/getting-started.md

@@ -23,7 +23,7 @@ cd data-hub
 uv sync --all-packages
 
 # Install web app dependencies.
-cd web-app && npm install && cd ..
+cd web && npm install && cd ..
 ```
 
 The Python workspace is managed by uv. The root `pyproject.toml` defines three workspace members — `lambda`, `watcher`, and `packages/shared` — and all are installed together by `uv sync --all-packages`.
@@ -35,7 +35,7 @@ The Python workspace is managed by uv. The root `pyproject.toml` defines three w
 The web app requires the following variables. The easiest way to get them is via the Vercel CLI:
 
 ```sh
-cd web-app
+cd web
 vercel env pull
 ```
 
@@ -72,7 +72,7 @@ The watcher reads its configuration from a YAML file at `~/.data-hub/config.yaml
 ## Database setup
 
 ```sh
-cd web-app
+cd web
 
 # Create a local PostgreSQL database.
 createdb data-hub-local
@@ -98,7 +98,7 @@ Other database commands:
 make dev
 
 # Or equivalently:
-cd web-app && npm run dev
+cd web && npm run dev
 ```
 
 The app runs at [http://localhost:3000](http://localhost:3000).

docs/lambda.md

@@ -54,7 +54,7 @@ Each processor module exposes a `process_file()` function that accepts the run I
 
 ## Slack notifications
 
-Slack notifications are sent by the **web app** (`web-app/lib/slack.ts`), not the Lambda. When the Lambda's `process_file` calls `POST /api/v1/instruments/:instrumentId/runs` to register a newly-detected run, that endpoint posts a single message per run to `SLACK_WEBHOOK_URL` (configured per environment in Vercel). Subsequent files for the same run do not re-notify because the upsert is idempotent on `(instrument_id, run_id)`. File-level failures remain visible in the web app via the file row's `status='failed'` and `error_message` fields.
+Slack notifications are sent by the **web app** (`web/lib/slack.ts`), not the Lambda. When the Lambda's `process_file` calls `POST /api/v1/instruments/:instrumentId/runs` to register a newly-detected run, that endpoint posts a single message per run to `SLACK_WEBHOOK_URL` (configured per environment in Vercel). Subsequent files for the same run do not re-notify because the upsert is idempotent on `(instrument_id, run_id)`. File-level failures remain visible in the web app via the file row's `status='failed'` and `error_message` fields.
 
 ## Adding a new instrument
 

docs/run-archives.md

@@ -45,7 +45,7 @@ Archives live in a separate bucket per environment, provisioned by [`infra/templ
 The fingerprint is a sorted SHA-256 of `(file_id, s3_key)` pairs:
 
 ```ts
-// web-app/lib/api/archive-builder.ts
+// web/lib/api/archive-builder.ts
 [...files].map((f) => `${f.id}:${f.s3Key}`).sort().join("|")
 ```
 
@@ -61,7 +61,7 @@ Properties this gives us:
 Two simultaneous "Download all" clicks must not double-invoke the Lambda. The schema enforces this with a *partial* unique index:
 
 ```sql
--- web-app/drizzle/0016_add_archive_jobs.sql
+-- web/drizzle/0016_add_archive_jobs.sql
 CREATE UNIQUE INDEX archive_jobs_inflight_unique_idx
   ON archive_jobs (instrument_run_id, fingerprint)
   WHERE status IN ('pending', 'building');

lambda/src/data_hub_lambda/handler.py

@@ -151,7 +151,7 @@ def _handle_build_archive(payload: dict[str, Any]) -> dict[str, Any]:
     """Run the archive builder and (optionally) PATCH the originating job.
 
     Sync callers (``payload["job_id"]`` absent) get the build result inline.
-    Async callers send ``"job_id"`` so the web-app job row gets PATCHed when
+    Async callers send ``"job_id"`` so the web app job row gets PATCHed when
     the build finishes — the HTTP response is the ack of acceptance and the
     actual outcome is delivered out-of-band.
     """
@@ -246,7 +246,7 @@ def _post_archive_job_status(
 
     Failures here are logged but never re-raised — the build itself succeeded
     or failed for its own reasons, and we don't want a callback failure to
-    mask that. The web-app's UI does not depend on this PATCH landing
+    mask that. The web app's UI does not depend on this PATCH landing
     either: it polls ``/download-archive`` which short-circuits on an S3
     HEAD, so a finished build is downloadable the moment the multipart
     upload completes.

packages/shared/src/data_hub_shared/testing.py

@@ -39,7 +39,7 @@
 _TOKEN_PREFIX = "dhub_"
 
 # testing.py lives at packages/shared/src/data_hub_shared/ — walk up 4 levels to the repo root.
-_WEB_APP_DIR = Path(__file__).resolve().parents[4] / "web-app"
+_WEB_DIR = Path(__file__).resolve().parents[4] / "web"
 
 
 # ---------------------------------------------------------------------------
@@ -115,7 +115,7 @@ def wait_for_server(
 
 
 # ---------------------------------------------------------------------------
-# Token helpers — must match web-app/lib/tokens.ts
+# Token helpers — must match web/lib/tokens.ts
 # ---------------------------------------------------------------------------
 
 
@@ -230,7 +230,7 @@ def start_test_server() -> Generator[IntegrationEnv, None, None]:
     # 2. Push the Drizzle schema.
     subprocess.run(
         ["npx", "drizzle-kit", "push", "--force"],
-        cwd=str(_WEB_APP_DIR),
+        cwd=str(_WEB_DIR),
         env={**os.environ, "DATABASE_URL": _DATABASE_URL},
         check=True,
         capture_output=True,
@@ -260,7 +260,7 @@ def start_test_server() -> Generator[IntegrationEnv, None, None]:
 
     build_result = subprocess.run(
         ["npx", "next", "build"],
-        cwd=str(_WEB_APP_DIR),
+        cwd=str(_WEB_DIR),
         env=server_env,
         capture_output=True,
     )
@@ -273,7 +273,7 @@ def start_test_server() -> Generator[IntegrationEnv, None, None]:
 
     server_proc = subprocess.Popen(
         ["npx", "next", "start", "-p", str(port)],
-        cwd=str(_WEB_APP_DIR),
+        cwd=str(_WEB_DIR),
         env=server_env,
         stdout=subprocess.PIPE,
         stderr=subprocess.PIPE,

watcher/tests/integration/test_update_check.py

@@ -1,6 +1,6 @@
 """Integration tests: watcher update-check endpoint via DataHubClient.
 
-The TS-side tests in `web-app/tests/integration/watchers.test.ts` cover
+The TS-side tests in `web/tests/integration/watchers.test.ts` cover
 the HTTP shape; this file ensures the Python `DataHubClient` plumbing
 parses the response into the typed `WatcherUpdateInfoResponse` model
 correctly so the CLI / in-process updater can consume it.