feat: overlay Skills, and five more Jev decisions (iterations 4 and 5)

Iteration 4:
- Overlay Skills (step 12): an Execution names an organisation's standards
  Skill from the folders the deployment configures; recorded with its version.
  An example standards Skill and an evaluation case that uses it.
- Lessons (step 10): a prove command that compares a run with lessons against
  one without, and triage of evidence an existing lesson already covers.

Iteration 5:
- Step 8: the references of a Specialist's Skills its task needs are named in
  its context as read_first.
- Step 14: a remote MCP server's reply that instructs the agent is withheld;
  the user's own text is flagged as a risk and nothing more.
- Step 15: in a Change request, items only reworded are listed apart from
  real changes.
- Step 19: each Execution's design recommendations are judged when it ends and
  the scores kept in its record. The evaluation takes its rubric from the same
  place.

Each question was calibrated against live Jev; none has run in a case. Steps
6, 7, 9, 13 and 18 stay planned, with the reasons in the plan map.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-09 17:45:56 +01:00
parent 844987587c
commit 567aede5ca
38 changed files with 1956 additions and 58 deletions

View File

@@ -56,6 +56,8 @@ class ExecutionState(TypedDict, total=False):
customer_case: str # the Customer case this Execution belongs to
intent_version: int # which statement of the case's intent started this Execution
workflow_request: str
risks: list[dict[str, Any]] # flags on what the user wrote, for a person to see
overlay_skills: dict[str, str] # overlay Skills this Execution loads -> version
baseline: dict[str, Any] | None # a Change request's Baseline, read from its files
pre_approved: bool
allow_cloud_read: bool | None
@@ -94,6 +96,8 @@ class ExecutionState(TypedDict, total=False):
idle_asks: int # questions put to the user running, with nothing changing between
ask_fingerprint: str # the Ledger's state when the user was last asked
decisions: list[dict[str, Any]] # every routing decision, in order
# How the design recommendations were judged when the Execution ended.
assessment: dict[str, Any] | None
turns: int
status: str # running | completed | completed_with_warnings