Garry Tanandcapy-ai[bot] 322906ab2b v1.92.79.0 fix: /plan-tune stops reporting mismatches with no observed answers behind them (#3436) (#3856) ...

* fix(plan-tune): compare declared and inferred only with 3+ observed answers (#3436)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test: derive keeps the gap at 3 events; changelog fragment for #3436

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(plan-tune): profile view and design doc honor the 3-answer floor (#3436)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(plan-tune): keep the 10-answer floor in --check-mismatch beside the per-dimension floor

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

2026-11-02 13:17:17 +00:00

..

sections

v1.91.276.0 feat(preamble): tier 2+ skills load the shared preamble once per session (GSTA-96) (#3434)

2026-10-27 13:28:18 +00:00

SKILL.md

v1.92.79.0 fix: /plan-tune stops reporting mismatches with no observed answers behind them (#3436) (#3856)

2026-11-02 13:17:17 +00:00

SKILL.md.tmpl

v1.92.79.0 fix: /plan-tune stops reporting mismatches with no observed answers behind them (#3436) (#3856)

2026-11-02 13:17:17 +00:00