v5.3.0: Standard names pipeline, DD lifecycle, and CI hardening

.github/agents/engineer.agent.md

@@ -84,6 +84,16 @@ When modifying LinkML schemas:
 - Documentation and prompt template updates
 - Refactors where the before/after is well-defined
 
+### Commonly-Modified Areas
+
+| Path | Purpose |
+|------|---------|
+| `imas_codex/sn/` | Standard name pipeline (mint, benchmark, graph ops) |
+| `tests/sn/` | SN test suite (mostly mock-based, no Neo4j required) |
+| `imas_codex/llm/prompts/sn/` | LLM prompt templates for SN |
+| `imas_codex/sn/benchmark_reference.py` | Gold reference set for benchmark scoring |
+| `imas_codex/sn/benchmark_calibration.yaml` | Calibration dataset for reviewer consistency |
+
 ## When to Escalate
 
 If a task requires:

.github/skills/project-dev/SKILL.md

@@ -84,6 +84,10 @@ git push origin main
 | `@pytest.mark.integration` | Full integration tests |
 | `@pytest.mark.unit` | Fast unit tests |
 
+SN tests live in `tests/sn/` and run with `uv run pytest tests/sn/ -v`. They do not require
+Neo4j unless marked `@pytest.mark.graph` — the rest use mocks. Benchmark tests validate prompt
+parity with the mint pipeline, calibration dataset integrity, and reference set coverage.
+
 ## Project Structure
 
 | Directory | Purpose |
@@ -95,7 +99,9 @@ git push origin main
 | `imas_codex/tools/` | MCP tool implementations |
 | `imas_codex/remote/` | Remote execution (SSH, scripts) |
 | `imas_codex/llm/` | LLM integration and prompt templates |
+| `imas_codex/sn/` | Standard name pipeline (mint, benchmark, graph ops) |
 | `tests/` | Test suite (mirrors source structure) |
+| `tests/sn/` | Standard name test suite (mostly mock-based) |
 | `plans/features/` | Active feature plans |
 | `agents/` | Agent documentation and schema reference |
 
@@ -107,3 +113,11 @@ git push origin main
 - **Model selection**: Use `get_model(section)` from `imas_codex.settings`
 - **Facility config**: Use `get_facility(facility)` — never hardcode facility values
 - **Remote execution**: Use `run_python_script()` from `imas_codex.remote.executor`
+
+### SN Key Files
+
+| File | Purpose |
+|------|---------|
+| `imas_codex/sn/benchmark_reference.py` | Gold reference set (52 entries across 8 IDSs) |
+| `imas_codex/sn/benchmark_calibration.yaml` | Known-quality examples for reviewer consistency |
+| `imas_codex/llm/prompts/sn/` | LLM prompt templates for mint, review, and benchmark |

.github/skills/service-ops/SKILL.md

@@ -75,6 +75,11 @@ uv run imas-codex llm spend           # Cost tracking
 uv run imas-codex llm logs            # View logs
 ```
 
+`sn mint` and `sn benchmark` require the LLM proxy to be running. Model names must use the
+`openrouter/` prefix (e.g. `openrouter/anthropic/claude-sonnet-4-5`) to preserve
+`cache_control` blocks — prompt caching is handled provider-side by OpenRouter, not by this
+codebase.
+
 ## SSH Tunnels
 
 ```bash

.github/workflows/benchmark.yml

@@ -1,8 +1,5 @@
 name: Benchmark
 
-env:
-  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
-
 on:
   push:
     tags: ["v*"]
@@ -54,7 +51,7 @@ jobs:
     steps:
       # ── Setup ──────────────────────────────────────────────────────────
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
 
@@ -94,7 +91,7 @@ jobs:
           df -h
 
       - name: Install UV + ASV
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v8.0.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
 

.github/workflows/container-cleanup.yml

@@ -16,7 +16,6 @@ on:
         type: boolean
 
 env:
-  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
   ACR_REGISTRY: crcommonallfrc.azurecr.io
   IMAGE_NAME: iterorganization/imas-codex
 

.github/workflows/docker-build-push.yml

@@ -11,11 +11,12 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
   GHCR_REGISTRY: ghcr.io
   ACR_REGISTRY: crcommonallfrc.azurecr.io
   IMAGE_NAME: ${{ github.repository }}
-  IMAS_DD_VERSION: "4.1.0"
+  # ACR image name is always the upstream path so Azure picks up fork RC
+  # builds. GHCR uses IMAGE_NAME (per-fork) — each fork has its own GHCR.
+  ACR_IMAGE_NAME: iterorganization/imas-codex
   # Graph OCI artifacts: try the repo owner's registry first (where
   # `imas-codex release` pushes them), fall back to the upstream org
   # registry for forks that haven't pushed their own graph yet.
@@ -52,7 +53,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Install oras CLI
         run: |
@@ -207,7 +208,7 @@ jobs:
 
       - name: Install uv
         if: steps.graph-tag.outputs.imas-tag != 'none'
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v8.0.0
         with:
           enable-cache: true
           github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -257,7 +258,7 @@ jobs:
 
       - name: Upload test results
         if: always() && steps.graph-tag.outputs.imas-tag != 'none'
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: graph-quality-results
           path: graph-quality-results.xml
@@ -270,7 +271,7 @@ jobs:
     if: startsWith(github.ref, 'refs/tags/') || github.event_name == 'workflow_dispatch'
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
 
@@ -316,16 +317,16 @@ jobs:
           echo "Container started, waiting for services..."
 
       - name: Wait for health check
-        timeout-minutes: 5
+        timeout-minutes: 10
         run: |
           echo "Waiting for MCP server to be ready..."
-          for i in $(seq 1 60); do
+          for i in $(seq 1 90); do
             if docker exec smoke-test curl -sf http://127.0.0.1:8000/health > /dev/null 2>&1; then
-              echo "✅ MCP server healthy after ${i}s"
+              echo "✅ MCP server healthy after $((i * 5))s"
               break
             fi
-            if [ $i -eq 60 ]; then
-              echo "❌ Health check timed out"
+            if [ $i -eq 90 ]; then
+              echo "❌ Health check timed out after 450s"
               docker logs smoke-test
               exit 1
             fi
@@ -436,7 +437,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0 # Full git history for dynamic versioning
           # Ensure all refs are available
@@ -528,7 +529,7 @@ jobs:
         id: meta-acr
         uses: docker/metadata-action@v5
         with:
-          images: ${{ env.ACR_REGISTRY }}/${{ env.IMAGE_NAME }}
+          images: ${{ env.ACR_REGISTRY }}/${{ env.ACR_IMAGE_NAME }}
           tags: |
             type=semver,pattern=v{{version}}${{ matrix.graph_variant.suffix }}
             type=semver,pattern=v{{major}}.{{minor}}${{ matrix.graph_variant.suffix }}
@@ -555,7 +556,6 @@ jobs:
             ${{ steps.meta-ghcr-rc.outputs.labels }}
           build-args: |
             IDS_FILTER=
-            IMAS_DD_VERSION=${{ env.IMAS_DD_VERSION }}
             GHCR_REGISTRY=${{ needs.graph-quality.outputs.graph-registry }}
             GRAPH_TAG=${{ steps.variant.outputs.graph-tag }}
             GRAPH_PACKAGE=${{ matrix.graph_variant.package }}
@@ -583,7 +583,6 @@ jobs:
             ${{ steps.meta-acr.outputs.labels }}
           build-args: |
             IDS_FILTER=
-            IMAS_DD_VERSION=${{ env.IMAS_DD_VERSION }}
             GHCR_REGISTRY=${{ needs.graph-quality.outputs.graph-registry }}
             GRAPH_TAG=${{ steps.variant.outputs.graph-tag }}
             GRAPH_PACKAGE=${{ matrix.graph_variant.package }}
@@ -641,7 +640,7 @@ jobs:
 
       - name: Generate artifact attestation for GHCR (releases only)
         if: github.event_name != 'pull_request' && startsWith(github.ref, 'refs/tags/v') && !contains(github.ref, '-rc')
-        uses: actions/attest-build-provenance@v1
+        uses: actions/attest-build-provenance@v4
         with:
           subject-name: ${{ env.GHCR_REGISTRY }}/${{ env.IMAGE_NAME }}
           subject-digest: ${{ steps.build-release.outputs.digest }}

.github/workflows/graph-quality.yml

@@ -29,7 +29,6 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
   NEO4J_PASSWORD: imas-codex
   NEO4J_URI: bolt://localhost:7687
 
@@ -58,7 +57,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Install oras CLI
         run: |
@@ -186,7 +185,7 @@ jobs:
             "MATCH (n) RETURN count(n) AS nodes, labels(n)[0] AS label ORDER BY nodes DESC LIMIT 10"
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v8.0.0
         with:
           enable-cache: true
           github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -230,7 +229,7 @@ jobs:
 
       - name: Upload test results
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: graph-quality-results
           path: graph-quality-results.xml

.github/workflows/release.yml

@@ -1,8 +1,5 @@
 name: Release
 
-env:
-  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
-
 on:
   push:
     tags:
@@ -23,12 +20,12 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v8.0.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
 
@@ -90,7 +87,7 @@ jobs:
           echo "tag_name=${TAG_NAME}" >> $GITHUB_OUTPUT
 
       - name: Create Release
-        uses: softprops/action-gh-release@v1
+        uses: softprops/action-gh-release@v2
         with:
           tag_name: ${{ steps.changelog.outputs.tag_name }}
           name: Release ${{ steps.changelog.outputs.tag_name }}

.github/workflows/test.yml

@@ -1,8 +1,5 @@
 name: Test
 
-env:
-  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
-
 on:
   push:
     branches: [main]
@@ -23,7 +20,7 @@ jobs:
         imas-dd-version: ["3.42.2", "4.1.0"]
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
 
       - name: Set up Node.js
         uses: actions/setup-node@v4
@@ -37,7 +34,7 @@ jobs:
           npx --version
 
       - name: Cache npm packages
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.npm
           key: npm-${{ runner.os }}-${{ hashFiles('.github/workflows/test.yml') }}
@@ -51,7 +48,7 @@ jobs:
         run: playwright install --with-deps chromium
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v8.0.0
         with:
           enable-cache: true
           github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -85,7 +82,7 @@ jobs:
           IMAS_DD_VERSION: ${{ matrix.imas-dd-version }}
 
       - name: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v6
         if: ${{ !cancelled() }}
         with:
           file: ./coverage.xml
@@ -116,10 +113,10 @@ jobs:
           --health-start-period 30s
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v8.0.0
         with:
           enable-cache: true
           github-token: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -8,7 +8,6 @@ __pycache__/
 imas_codex/graph/models.py
 imas_codex/graph/schema_context_data.py
 imas_codex/config/models.py
-imas_codex/core/physics_domain.py
 agents/schema-reference.md
 
 # Generated index files

.mcp.json

@@ -1,11 +1,16 @@
 {
-  "mcpServers": {
+  "servers": {
+    "imas-dd": {
+      "type": "stdio",
+      "command": "uv",
+      "args": ["run", "imas-codex", "serve", "--dd-only"]
+    },
     "codex": {
       "type": "stdio",
       "command": "uv",
       "args": ["run", "imas-codex", "serve"]
     },
-    "imas": {
+    "imas-prod": {
       "type": "http",
       "url": "https://imas-dd.iter.org/mcp"
     },

.vscode/mcp.json

@@ -0,0 +1 @@
+../.mcp.json