`report.sh --full` always dumped kv-calc's full catalog-wide calibration
matrix (4 models × every compose), regardless of what the reporter runs, and
the vLLM-only skip didn't cover ik_llama. Three fixes:
(a) Scope to the running model. Resolve the active container -> kv-calc model
id and filter `--calibration` output to that model's `== <id> ==` section.
A Qwen single-card reporter no longer gets Gemma/MoE rows.
(b) Fix the ggml-engine skip. The skip only matched `llama-cpp-*`; `ik-llama-*`
fell through to "unknown" and ran the (inapplicable) calibration anyway.
Both ggml engines now emit the skip note.
(c) Opt-in full matrix. `--full-calibration` (or REPORT_FULL_CALIBRATION=1)
restores the catalog-wide matrix for maintainer triage. Unknown/unresolved
model also falls back to the full matrix.
Logic is factored into a pure, side-effect-free lib (scripts/lib/report_calib.sh:
calib_engine_for_container / calib_model_for_container / calib_filter_model_section)
so it's unit-testable. New test scripts/tests/test-report-calib.sh covers the
engine map (incl. the ik_llama regression), the model map (all 4 models), and
the section filter (keeps banner + target section + Overall, drops others;
empty id = passthrough).
Validated: bash -n; test-report-calib ok; live `kv-calc --calibration` scoped to
qwen3.6-27b keeps only that section + the Overall line.
Closes#168.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
