2 Commits

Include renames

Author	SHA1	Message	Date
4 people	fc1d11839c	feat(skills): consolidate Itô market skills into ito-baskets; align ito-training fail-closed contract (#2770) ... * feat(skills): consolidate Itô market skills into ito-baskets; align ito-training fail-closed contract - Replace ito-basket-compare, ito-market-intelligence, ito-data-atlas-agent, and ito-trade-planner with one read-only ito-baskets skill (index, compare, brief, worksheet modes) preserving every non-advisory, provenance, freshness, and recovery contract - Extend the GET-only client with anonymous basket-index/basket-detail commands that validate the ito.public_basket_read.v1 contract and never transmit a credential to public routes - Rewrite ito-training to the same fail-closed availability-check structure as ito-inference: pre-spawn rejection, server-verified booking entitlement, opaque confirmation-ref, manifest digest binding, idempotent lifecycle - Update install module, npm files, README/docs catalog counts (287 -> 284), and add consolidated contract tests * test: anchor Itô API origin assertion (CodeQL js/regex/missing-regexp-anchor) * test: avoid URL-literal substring assertion (CodeQL js/incomplete-url-substring-sanitization) * fix: apply CodeRabbit auto-fixes Fixed 1 file(s) based on 1 unresolved review comment. Co-authored-by: CodeRabbit <noreply@coderabbit.ai> --------- Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Co-authored-by: CodeRabbit <noreply@coderabbit.ai>	2026-08-12 15:52:26 -04:00
3 people	fd27a0ec9f	Add ito-inference and ito-training skills (delegate to canonical Itô backend) (#2700) ... Two ECC skills chaining off an ito-compute booking, per the Full-Stack Harness Engineering Plan (2026-08-06): - ito-inference: serve a model on booked GPUs via ecc ito serve (Layer 0.2). - ito-training: run a staged, eval-gated training pipeline via ecc ito train (Layer 0.3). Both match the existing ito-compute skill: origin ECC, delegate to the canonical CLI/backend, implement no parallel serving/training stack, chain off a completed booking, and never book, reserve, or spend. They report the missing capability while the desk serve-on-booking / training-run backends are scaffolds. Co-authored-by: Affaan Mustafa <affaan@itomarkets.com>	2026-08-07 12:46:06 -04:00