docs: mark northflank smoke pass

README.md

@@ -35,10 +35,10 @@ Implementation status:
 - [x] Re-run the baseline comparison on the `constellaration`-backed branch state
 - [x] Replace the synthetic evaluator with `constellaration`
 - [x] Add a runnable Northflank smoke workflow and note
+- [x] Pass the Northflank smoke test on the H100 workspace
 - [ ] Add tracked `P1` fixtures under `server/data/p1/`
 - [ ] Run manual playtesting and record the first reward pathology
 - [ ] Refresh the heuristic baseline for the real verifier path
-- [ ] Pass the Northflank smoke test on the H100 workspace
 - [ ] Deploy the real environment to HF Space
 
 ## Known Gaps
@@ -107,10 +107,7 @@ uv sync --extra notebooks
 1. Add tracked `P1` fixtures under `server/data/p1`.
 2. Run manual playtest episodes and record the first real reward pathology, if any.
 3. Refresh the heuristic baseline using manual playtest evidence, then save one comparison trace.
-4. Pass a Northflank smoke test:
-   - import `constellaration`
-   - run one rotating-ellipse generation plus one low-fidelity verifier call
-   - write an artifact to persistent storage
+4. Use the passing Northflank H100 setup to produce remote traces and comparisons from the real verifier path.
 5. Deploy the environment to HF Space.
 6. Add the Colab notebook under `training/notebooks`.
 

docs/FUSION_DELIVERABLES_MAP.md

@@ -12,6 +12,7 @@ Use this map to sequence execution, not to reopen already-locked task choices.
 - [x] official `constellaration` verifier loop is wired
 - [x] baseline comparison has been rerun on the real verifier path
 - [x] Northflank smoke workflow and note are committed
+- [x] Northflank smoke test has passed on the team H100
 - [ ] tracked fixtures are checked in
 - [ ] manual playtest evidence exists
 - [ ] heuristic baseline has been refreshed for the real verifier path
@@ -101,12 +102,12 @@ flowchart LR
 
 ## Priority Order
 
+Northflank compute bring-up and smoke validation are complete.
+
 1. Add tracked fixtures and run fixture sanity checks.
 2. Manual-playtest the environment and record the first real pathology, if any.
 3. Refresh the heuristic baseline from that evidence.
-4. Bring up the Northflank H100 workspace with persistent storage.
-5. Pass the Northflank smoke test.
-6. Make one stable OpenEnv `P1` task work remotely with clear, reproducible rules.
-7. Use the notebook to show traces and comparisons; include training only if it adds signal.
-8. Record the demo around environment clarity, verifier fidelity, reward shaping, and one stable trajectory.
-9. Polish the repo only after the artifacts are real.
+4. Make one stable OpenEnv `P1` task work remotely with clear, reproducible rules.
+5. Use the notebook to show traces and comparisons; include training only if it adds signal.
+6. Record the demo around environment clarity, verifier fidelity, reward shaping, and one stable trajectory.
+7. Polish the repo only after the artifacts are real.

docs/FUSION_DESIGN_LAB_PLAN_V2.md

@@ -13,6 +13,7 @@
 - [x] post-terminal `step()` guard is in place
 - [x] baseline comparison has been rerun on the real verifier path
 - [x] Northflank smoke workflow and note are committed
+- [x] Northflank smoke test has passed on the team H100
 - [ ] tracked `P1` fixtures are added
 - [ ] manual playtest evidence is recorded
 - [ ] heuristic baseline is refreshed for the real verifier path
@@ -479,6 +480,7 @@ The repo should make the environment easy to understand:
 - notebook starts on the team H100
 - persistent storage mount is usable
 - smoke test artifact is written successfully
+- latest artifact example: `/home/jovyan/fusion-design-lab/smoke/northflank_smoke_20260308T023646Z.json`
 
 ### Gate 1: Environment Contract Locked
 

docs/FUSION_NEXT_12_HOURS_CHECKLIST.md

@@ -15,6 +15,7 @@ Do not expand scope beyond one stable task. Training is supporting evidence, not
 - [x] replace the synthetic evaluator with `constellaration`
 - [x] re-run baselines on the real verifier path
 - [x] commit the Northflank smoke workflow and note
+- [x] pass the Northflank smoke test on the team H100
 - [ ] add tracked fixtures and manual playtest evidence
 - [ ] refresh the heuristic baseline after the real-verifier rerun
 
@@ -41,11 +42,12 @@ Carry these rules through the whole checklist:
 
 1. Bring up the Northflank Jupyter Notebook with PyTorch on the team H100.
 2. Attach persistent storage before relying on saved models, caches, or fixture downloads.
-3. Pass a concrete smoke test:
+3. Preserve the concrete smoke-test evidence:
    - import `constellaration`
    - generate one rotating-ellipse boundary
    - run one low-fidelity verifier call
-   - write one artifact to persistent storage
+   - keep one artifact in persistent storage
+   - current artifact: `/home/jovyan/fusion-design-lab/smoke/northflank_smoke_20260308T023646Z.json`
 
 Exit condition: the notebook is not just open; the verifier path works and persistent storage is usable.
 

training/notebooks/README.md

@@ -16,6 +16,7 @@ Recommended split:
 
 - [x] Northflank smoke notebook note saved
 - [x] runnable Northflank smoke script saved
+- [x] Northflank smoke test passed on the team H100
 - [ ] manual-playtest notebook or trace notebook saved
 - [ ] thin public Colab notebook saved
 
@@ -37,5 +38,6 @@ Runnable repo path:
 
 - `uv run python training/notebooks/northflank_smoke.py --output-dir <mounted-persistent-storage-path>`
 - note: `training/notebooks/NORTHFLANK_SMOKE_NOTE.md`
+- latest passing artifact example: `/home/jovyan/fusion-design-lab/smoke/northflank_smoke_20260308T023646Z.json`
 
 The notebooks are supporting evidence for the environment, not the primary product.