Merge pull request #38 from NatLabRockies/develop

v0.8.2

Author: brianlball

.claude/skills/measure-authoring/SKILL.md

@@ -34,6 +34,9 @@ create_measure(
 ```
 test_measure(measure_dir="/runs/custom_measures/set_lights_8w")
 ```
+Tests run against the currently loaded model (or SystemD_baseline.osm fallback),
+so measures that depend on HVAC, plant loops, or zones will work correctly.
+Use `model_path` to test against a specific model.
 
 ### 3. Apply to Model
 ```
@@ -103,6 +106,40 @@ extract_summary_metrics(run_id=<retrofit_id>)   # compare to baseline
 
 WARNING: Beams are AIR TERMINALS (connect via `air_loop.addBranchForZone`), NOT zone equipment (`addToThermalZone`).
 
+## ReportingMeasures
+
+ReportingMeasures run **after simulation** and access SQL results. Use when the user wants to
+generate custom reports, extract specific metrics, or post-process simulation output.
+
+### Create a ReportingMeasure
+```
+create_measure(
+    name="custom_eui_report",
+    description="Extract and report custom EUI breakdown",
+    language="Ruby",
+    measure_type="ReportingMeasure",
+    run_body='    query = "SELECT Value FROM TabularDataWithStrings WHERE ReportName=\'AnnualBuildingUtilityPerformanceSummary\' AND TableName=\'Site and Source Energy\' AND RowName=\'Total Site Energy\' AND ColumnName=\'Total Energy\' AND Units=\'GJ\'"\n    val = sql.execAndReturnFirstDouble(query)\n    if val.is_initialized\n      runner.registerValue("total_site_energy_gj", val.get)\n      runner.registerInfo("Total Site Energy: #{val.get} GJ")\n    end\n    runner.registerFinalCondition("Report complete")'
+)
+```
+
+### Test with Simulation Results
+```
+# ReportingMeasures need SQL — provide run_id from a completed sim
+test_measure(measure_dir="/runs/custom_measures/custom_eui_report", run_id="<completed_run_id>")
+```
+Without `run_id`, only argument validation tests run (no `run()` execution).
+
+### Apply to Completed Simulation
+```
+apply_measure(measure_dir="/runs/custom_measures/custom_eui_report", run_id="<completed_run_id>")
+```
+
+### Key Differences from ModelMeasure
+- `run()` signature: `(runner, user_arguments)` — no `model` param
+- Model & SQL boilerplate is auto-generated: `model` and `sql` variables are available in run_body
+- `arguments()` takes no params (not `model`)
+- Includes empty `energyPlusOutputRequests()` stub (edit via `edit_measure` if needed)
+
 ## Notes
 
 - `run_body` indentation matters: Ruby = 4 spaces, Python = 8 spaces

.claude/skills/tool-workflows/SKILL.md

@@ -120,6 +120,26 @@ extract_summary_metrics(run_id=<retrofit_id>)
 
 See the `measure-authoring` skill for run_body patterns and language guidance.
 
+## Write and Apply a Custom ReportingMeasure
+
+ReportingMeasures run after simulation to analyze SQL results.
+
+```
+# 1. Run simulation first
+run_simulation(osm_path="/runs/model.osm", epw_path="<epw>")
+
+# 2. Create reporting measure
+create_measure(name="custom_report", description="...",
+    language="Ruby", measure_type="ReportingMeasure",
+    run_body="    val = sql.execAndReturnFirstDouble('SELECT ...')\n    runner.registerValue('metric', val.get) if val.is_initialized")
+
+# 3. Test against completed simulation
+test_measure(measure_dir="/runs/custom_measures/custom_report", run_id="<run_id>")
+
+# 4. Apply to completed simulation
+apply_measure(measure_dir="/runs/custom_measures/custom_report", run_id="<run_id>")
+```
+
 ## Object Cleanup
 
 ```

.github/workflows/ci.yml

@@ -72,7 +72,7 @@ jobs:
               ;;
             3)
               # controls, object mgmt, loads, building, doas, hvac, measures, measure_authoring, skill_qaqc, hvac_supply_wiring
-              FILES="tests/test_component_controls.py tests/test_object_management.py tests/test_generic_access.py tests/test_create_loads.py tests/test_building.py tests/test_doas_system.py tests/test_hvac.py tests/test_measures.py tests/test_measure_authoring.py tests/test_skill_qaqc.py tests/test_hvac_supply_wiring.py"
+              FILES="tests/test_component_controls.py tests/test_object_management.py tests/test_generic_access.py tests/test_create_loads.py tests/test_building.py tests/test_doas_system.py tests/test_hvac.py tests/test_measures.py tests/test_measure_authoring.py tests/test_skill_qaqc.py tests/test_hvac_supply_wiring.py tests/test_validate_model.py"
               EXTRA_ENV=""
               ;;
             4)

AGENTS.md

@@ -1,7 +1,7 @@
 # AGENTS.md — Codex CLI Instructions
 
 ## Project
-OpenStudio MCP server — 22 skills, 126 tools, ~14K prod lines.
+OpenStudio MCP server — 24 skills, 138 tools, ~18K prod lines.
 
 ## Architecture
 - `mcp_server/skills/<name>/tools.py` — MCP tool defs, calls operations
@@ -16,6 +16,7 @@ OpenStudio MCP server — 22 skills, 126 tools, ~14K prod lines.
 - No `getattr()` for OpenStudio API calls — every method must be explicit
 - No `shell=True` in subprocess calls
 - Tool functions use `_tool` suffix internally, MCP name strips it
+- `list[str]` params use `list[str] | str` type + `parse_str_list()` from `osm_helpers.py` (MCP clients may send JSON strings)
 
 ## Review Focus
 When reviewing code, check for: