Merge dev into main

.github/workflows/docs.yaml

@@ -1,62 +1,79 @@
-name: Docs
+name: Deploy Site & Docs
 
 on:
   push:
-    branches: [main]
+    branches: [main, dev]
   pull_request:
     paths:
       - docs/**
+      - site/**
+      - tasks/**/tools.py
+      - tasks/**/score.py
+      - tasks/**/env.py
+      - tasks/**/environments/**/tasks_json/**
+      - tasks/**/environments/**/subtasks_json/**
       - pyproject.toml
+      - mkdocs.yaml
   workflow_dispatch:
 
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages
+  cancel-in-progress: false
+
 jobs:
-  docs:
+  build:
     runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pages: write
-      id-token: write
-
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
+        with:
+          lfs: true
 
       - name: Set up Python 3.10
         uses: actions/setup-python@v5
         with:
           python-version: "3.10"
-          cache: "pip"
-          cache-dependency-path: |
-            pyproject.toml
-            requirements*.txt
 
-      - name: Get pip cache dir
-        id: pip-cache
-        run: echo "dir=$(pip cache dir)" >> $GITHUB_OUTPUT
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
 
-      - name: Cache pip dependencies
-        uses: actions/cache@v3
-        with:
-          path: ${{ steps.pip-cache.outputs.dir }}
-          key: ${{ runner.os }}-pip-docs-${{ hashFiles('pyproject.toml', 'requirements*.txt') }}
-          restore-keys: |
-            ${{ runner.os }}-pip-docs-
+      - name: Install dependencies
+        run: |
+          uv sync --extra docs
 
-      - name: Cache mkdocs
-        uses: actions/cache@v3
-        with:
-          path: .cache/mkdocs
-          key: ${{ runner.os }}-mkdocs-${{ hashFiles('docs/**') }}
-          restore-keys: |
-            ${{ runner.os }}-mkdocs-
+      - name: Generate landing-page data
+        run: uv run python site/extract_data.py
 
-      - name: Install dependencies
+      - name: Build MkDocs into docs/ subdirectory
+        run: uv run mkdocs build --site-dir _build/docs
+
+      - name: Assemble site
         run: |
-          python -m pip install --upgrade pip wheel setuptools
-          pip install -e ".[docs]"
+          mkdir -p _build
+          cp site/index.html _build/
+          cp site/data.js _build/
+          cp site/traces.js _build/
+          cp site/annotator.js _build/
+          cp site/corral_logo.png _build/
+          cp site/corral_arch.png _build/
 
-      - name: Build docs
-        run: mkdocs build
+      - name: Upload Pages artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: _build
 
-      - name: Deploy docs
-        run: mkdocs gh-deploy --force
-        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+  deploy:
+    if: github.event_name == 'push' && (github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev')
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.github/workflows/tests.yaml

@@ -34,7 +34,7 @@ jobs:
           uv pip install pre-commit
 
       - name: Cache pre-commit hooks
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pre-commit
           key: pre-commit-${{ hashFiles('.pre-commit-config.yaml') }}
@@ -128,8 +128,7 @@ jobs:
       - name: Install task dependencies
         run: |
           # Install the task package in development mode
-          # For src layouts, ensure editable install works properly
-          uv pip install -e . --force-reinstall
+          uv pip install -e .
         working-directory: ./tasks/${{ matrix.task }}
 
       - name: Run task tests
@@ -140,19 +139,89 @@ jobs:
           uv run python -m pytest tests -v --rootdir=.
         working-directory: ./tasks/${{ matrix.task }}
 
+  # Discover tasks with env.py files for server setup checking
+  discover-env-tasks:
+    needs: code-quality
+    runs-on: ubuntu-latest
+    outputs:
+      tasks: ${{ steps.discover.outputs.tasks }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Discover tasks with env.py (excluding those requiring special setup)
+        id: discover
+        run: |
+          # Excluded tasks:
+          #   retrosynthesis - requires a running database
+          #   afm            - requires nanosurf (Windows-only hardware library)
+          #   wetlab         - requires reaktoro (conda-only, not on PyPI)
+          #   samplemath     - uses bare imports incompatible with package-level import
+          EXCLUDED="retrosynthesis afm wetlab samplemath"
+          tasks=$(find tasks -maxdepth 1 -type d | while read task_dir; do
+            task_name=$(basename "$task_dir")
+            if [[ "$task_name" == "tasks" ]]; then continue; fi
+            if echo "$EXCLUDED" | grep -qw "$task_name"; then continue; fi
+            if [[ ! -f "$task_dir/pyproject.toml" ]]; then continue; fi
+            if find "$task_dir" -name "env.py" -maxdepth 4 -type f | grep -q .; then
+              echo "$task_name"
+            fi
+          done | sort | jq -R -s -c 'split("\n")[:-1]')
+          echo "tasks=$tasks" >> $GITHUB_OUTPUT
+          echo "Found env tasks: $tasks"
+
+  # Check that each task's env server can be set up correctly
+  check-env-servers:
+    needs: [discover-env-tasks, code-quality]
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        task: ${{ fromJson(needs.discover-env-tasks.outputs.tasks) }}
+
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          lfs: true
+
+      - name: Ensure Git LFS is initialized
+        run: |
+          git lfs install
+          git lfs pull --exclude="" || echo "Some LFS objects missing, continuing..."
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+
+      - name: Install root project (corral)
+        run: uv sync --all-extras --dev
+
+      - name: Install task dependencies
+        run: uv pip install -e .
+        working-directory: ./tasks/${{ matrix.task }}
+
+      - name: Check env server setup
+        run: |
+          uv run python -c "from ${{ matrix.task }} import env; print('Server setup OK')"
+        working-directory: ./tasks/${{ matrix.task }}
+
   # Summary job to check all results
   test-summary:
-    needs: [test-main, test-tasks]
+    needs: [test-main, test-tasks, check-env-servers]
     runs-on: ubuntu-latest
     if: always()
     steps:
       - name: Check test results
         run: |
-          if [[ "${{ needs.test-main.result }}" == "success" ]] && [[ "${{ needs.test-tasks.result }}" == "success" ]]; then
+          env_result="${{ needs.check-env-servers.result }}"
+          if [[ "${{ needs.test-main.result }}" == "success" ]] && \
+             [[ "${{ needs.test-tasks.result }}" == "success" ]] && \
+             [[ "$env_result" == "success" || "$env_result" == "skipped" ]]; then
             echo "✅ All tests passed!"
           else
             echo "❌ Some tests failed:"
             echo "Main tests: ${{ needs.test-main.result }}"
             echo "Task tests: ${{ needs.test-tasks.result }}"
+            echo "Env server checks: $env_result"
             exit 1
           fi

.gitignore

@@ -2,7 +2,6 @@
 .cache/
 docs/reference/*
 *doctrees*
-/site
 
 # Python ignores
 __pycache__/
@@ -62,6 +61,7 @@ dmypy.json
 # Environments
 .env
 .venv
+.micromamba/
 venv/
 env/
 ENV/
@@ -71,27 +71,57 @@ venv.bak/
 
 prompts.py
 
-**/run_react_agent.py
-**/run_tool_calling_agent.py
-
 # dev
 
+.metaflow
 notebooks
 results.json
 
+.code2latex_cache/
 .promptstore/
 prompts.py
 *.log
+*.aux
 *results.json
 agent_logs-ConcreteAgent-test-model-brief
 CORRAL_WORK_DIR
 CORRAL_WORK_DIR/*
 */CORRAL_WORK_DIR/*
 graph_output/
 benchmark_checkpoints
-agent_logs
-results/
+results
 nmrshiftdb2withsignals.sd
 plots/results
 wandb
 questions_resistor.json
+
+reports/corral_md_visualisation/**/*.py
+
+reports/corral_md_visualisation/**/logprobs_*/
+reports/corral_md_visualisation/**/metrics_*/
+
+reports_v2/**/logprobs*/
+other_examples.json
+logprobs_perplexity_data.json
+analysis/results/
+
+
+
+results/**/*.jsonl
+results/**/*.csv
+results/**/*.nc
+results/**/*.png
+results/**/*.tex
+results/**/*.pdf
+results/**/*.html
+results/**/*.md
+results/**/*.txt
+results/**/*.log
+results/**/*.err
+results/**/*.out
+results/**/*.log.gz
+
+**/.snakemake/
+analysis/*/
+reasoning_reports_old
+.claude/*

.pre-commit-config.yaml

@@ -28,6 +28,22 @@ repos:
       - id: blacken-docs
         exclude: ^tasks/(?!.*/src/).*
 
+  - repo: local
+    hooks:
+      - id: check-env-convention
+        name: check environment convention
+        entry: python scripts/check_env_convention.py
+        language: python
+        pass_filenames: false
+        files: ^tasks/
+      - id: validate-tool-docstrings
+        name: Validate @tool docstrings
+        entry: python3 scripts/validate_tool_docstrings.py
+        language: system
+        files: (tools\.py$|src/corral/utils/.*_tools\.py$)
+        exclude: ^tests/
+        pass_filenames: true
+
   - repo: https://github.com/commitizen-tools/commitizen
     rev: v4.8.0
     hooks: