diff --git a/.agents/skills/add-model-02-parity/SKILL.md b/.agents/skills/add-model-02-parity/SKILL.md
index 5a96f34a56..1bdace75d3 100644
--- a/.agents/skills/add-model-02-parity/SKILL.md
+++ b/.agents/skills/add-model-02-parity/SKILL.md
@@ -191,6 +191,7 @@ Tolerance guide:
 | Single block, same kernel | `1e-4` / `1e-4` | Tight default. |
 | Full DiT, aligned kernels | `1e-2` / `1e-2` | Cross-layer accumulation. |
 | Full DiT, cross-kernel bf16 | `0.1` / `0.1` | Also require abs-mean drift below 5% and per-modality diagnostics. |
+| Very deep DiT (50+ layers), bf16 | `0.5` / `0.0` | Tail errors from per-GEMM bf16 epsilon (~7.8e-3) accumulated across all layers. Must justify via diagnostic prints — see below. |
 | VAE decode fp32 | `5e-2` / `5e-2` | After normalization alignment. |
 | Encoder wrapper around same HF class | `1e-3` / `1e-3` | Should be near-zero. |
 
@@ -203,6 +204,39 @@ hooks. Use `docs/contributing/activation_trace.md` to keep
 `FASTVIDEO_TRACE_LAYERS`, `FASTVIDEO_TRACE_STATS`, and `FASTVIDEO_TRACE_STEPS`
 identical across FastVideo and upstream traces.
 
+### Calibrating atol > 0.1
+
+When a deep DiT (e.g. FLUX with 57 transformer blocks) produces `max_diff > 0.1`
+under bf16, do not silently bump `atol` to make the test pass. Print four metrics
+and assert that the *distribution* — not just the max — looks healthy:
+
+```python
+abs_diff = (hf_out.float().cpu() - fv_out.float().cpu()).abs()
+max_diff = abs_diff.max().item()
+mean_diff = abs_diff.mean().item()
+median_diff = abs_diff.median().item()
+p99_diff = torch.quantile(abs_diff.flatten(), 0.99).item()
+print(
+    f"max_diff={max_diff:.4f}  mean_diff={mean_diff:.4f}  "
+    f"median_diff={median_diff:.4f}  p99_diff={p99_diff:.4f}"
+)
+```
+
+Call `.item()` before formatting (older PyTorch versions do not implement
+`__format__` on 0-dim tensors), and prefer `torch.quantile` over
+`kthvalue(int(0.99 * N))` — `kthvalue` is 1-indexed and degenerates for
+very small `N`, while `quantile` handles the distribution boundary
+cleanly.
+
+Healthy bf16-tail signature (FLUX, 57 layers, observed on A40):
+`max=0.5, mean=0.04, median=0, p99=0.25`. Median near zero and mean ≪ atol
+prove the bulk of elements match — only the tail diverges due to accumulation.
+
+Real bug signature: `mean_diff >> 0.1` or `median_diff > 0.01`. Wrong weights,
+swapped layers, or missing residuals push the mean up, not just the max. Keep
+the diagnostic print in the committed test so reviewers can verify the
+calibration without rerunning.
+
 Useful local commands:
 
 ```bash
diff --git a/.agents/skills/add-model-09-pipeline/SKILL.md b/.agents/skills/add-model-09-pipeline/SKILL.md
index e91257b0a6..24ad0cfa53 100644
--- a/.agents/skills/add-model-09-pipeline/SKILL.md
+++ b/.agents/skills/add-model-09-pipeline/SKILL.md
@@ -69,10 +69,28 @@ Use this mode first.
    Runtime pipeline resolution is exact: `model_index.json["_class_name"]` must
    match a registered `EntryClass.__name__`, or a wrapper/alias class in
    `EntryClass`. Registry detectors do not select the executable pipeline class.
-4. Add new public generation kwargs to `fastvideo/api/sampling_param.py` before
-   examples or presets use them. `SamplingParam.update()` ignores unknown keys
-   except for logging, and preset defaults apply only to declared fields. Add CLI
-   args when the option should be available from command-line entrypoints.
+4. Add new public generation kwargs across the **full schema-parity surface**
+   before examples or presets use them. A missed surface fails CI in a different
+   way each time, so touching all four in one commit prevents three follow-ups:
+   - `fastvideo/api/sampling_param.py` — `SamplingParam.update()` ignores unknown
+     keys except for logging, and preset defaults apply only to declared fields.
+     Add CLI args here when the option should be available from command-line
+     entrypoints (note: the inference CLI is now config-only — most new fields
+     are reached via dotted overrides, not new flags).
+   - `fastvideo/api/schema.py` — add the field to `SamplingConfig` with the same
+     default. `test_inventory_targets_exist_in_typed_schema` walks
+     `request.sampling.<field>` and will assert-fail if the dataclass is missing
+     the attribute.
+   - `docs/design/inference_schema_parity_inventory.yaml` — register the field
+     under `surfaces.sampling_param_base.moved` with target
+     `request.sampling.<field>`. If the field has a live CLI dest (rare under
+     the config-only CLI), also add it to `cli.generate.expected_dests`
+     alphabetically, otherwise `test_cli_dest_inventory_matches_live_parsers`
+     fails.
+   - `fastvideo/tests/api/test_parser.py` —
+     `test_load_run_config_supports_yaml_roundtrip` compares an exact hardcoded
+     dict snapshot of every `SamplingConfig` field. Add the new field with its
+     default value in declaration order, or the dict-equality assertion fails.
 5. Put loader-time changes in `load_modules()` or earlier, not
    `initialize_pipeline()`. `ComposedPipelineBase.__init__` loads modules before
    `post_init()` calls `initialize_pipeline()`, so process-global flags, loader
diff --git a/.agents/skills/seed-ssim-references/SKILL.md b/.agents/skills/seed-ssim-references/SKILL.md
index 527b76ef98..b1b8ab81d8 100644
--- a/.agents/skills/seed-ssim-references/SKILL.md
+++ b/.agents/skills/seed-ssim-references/SKILL.md
@@ -19,6 +19,15 @@ side-by-side per `(model_id, backend, prompt)`:
   metadata + `slice_spec` + `format_version`) for tests that call
   `run_text_to_latent_similarity_test` in `latent_similarity_utils.py`.
   Compared via cosine distance on the slice and the full tensor.
+- **`.png`** — pixel ground-truth for **T2I / I2I** tests. `VideoGenerator`
+  emits a `.png` (not a `.mp4`) whenever `workload_type.value.endswith("2i")`
+  is true (`fastvideo/entrypoints/video_generator.py::_is_image_workload`).
+  **The SSIM helpers in `inference_similarity_utils.py` on current main
+  hardcode `.mp4`** (`_find_reference_video` filter, `output_video_name`
+  format). To consume `.png` references through the SSIM path, the test
+  must call a helper variant that accepts a `media_extension` parameter
+  (added in PR #1321). Until that lands on main, T2I SSIM coverage is
+  blocked at the helper layer.
 
 This skill:
 
@@ -111,6 +120,32 @@ and 6 are artefact-type-agnostic — `_iter_reference_files`,
 `copy_generated_to_reference`, and `upload_reference_videos` already walk
 both `.mp4` and `.pt` (see `reference_videos_cli.py`).
 
+**T2I / I2I gotcha:** when the helper produces a `.png` (any workload
+whose `workload_type.value` ends in `2i`), `reference_videos_cli.py copy-local`
+currently walks `.mp4` / `.pt` only and reports `0 copied files` without
+erroring. After step 5, verify the destination contains the seeded file;
+if it's empty, copy the PNG manually:
+
+```bash
+mkdir -p fastvideo/tests/ssim/reference_videos/default/L40S_reference_videos/<model_id>/<backend>/
+cp ./generated_videos_modal/default/generated_videos/L40S_reference_videos/<model_id>/<backend>/*.png \
+   fastvideo/tests/ssim/reference_videos/default/L40S_reference_videos/<model_id>/<backend>/
+```
+
+`git add -f` is **not required for the HF upload path**:
+`reference_videos_cli.py upload` calls `huggingface_hub.upload_folder` on
+the filesystem directly (`reference_videos_cli.py:311`) — git tracking
+status is irrelevant for `pytest fastvideo/tests/ssim/` reference sync.
+
+If you *also* want to commit the PNG locally, note that
+`fastvideo/tests/ssim/reference_videos/**` (catch-all near `.gitignore:94`)
+overrides the earlier `!fastvideo/tests/ssim/reference_videos/**/*.mp4`
+negation at `.gitignore:73`. Every reference file in this dir currently
+requires `git add -f`, regardless of extension. Fixing this properly
+means moving the `!...reference_videos/**/*.{mp4,pt,png}` negations
+*after* the catch-all (or removing the catch-all). Until then, `git add -f`
+is the standing workaround for committing references locally.
+
 If either check fails, stop and tell the user what's wrong.
 
 ### 2. Run the test on Modal L40S