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

@@ -54,6 +54,13 @@ class Settings(BaseSettings):
A2A_PUBLIC_URL: str | None = None # advertised in the agent card
ORCHESTRATOR_BUDGET: int = 40
SPECIALIST_BUDGET: int = 15
# Where overlay Skills live: an organisation's standards or one engagement's
# constraints, each an Agent Skill (ADR-0004). Comma-separated folders, relative
# to the repository root. A caller names an overlay; it can never supply one.
OVERLAY_SKILLS_DIRS: str = "skills/overlays"
# Overlay Skills every Execution loads, comma-separated.
DEFAULT_OVERLAY_SKILLS: str = ""
# Give Specialists the lessons Skill. Off runs without anything learned, which
# is how the evaluation shows whether a lesson helps.
LESSONS_ENABLED: bool = True
@@ -100,10 +107,39 @@ class Settings(BaseSettings):
# How directly a change must affect a pillar for its advisor to be consulted
# again: 0 not at all, 1 only indirectly, 2 directly.
JEV_PILLAR_THRESHOLD: float = 1.5
# In a Change request: at or below this probability of a real change, an item
# whose text differs from the Baseline's is listed as reworded, not changed.
JEV_REWORDED_THRESHOLD: float = 0.25
# Name, in a Specialist's context, the references of its Skills its task needs.
# A reference is named at this score or above: 0 not needed, 1 might help,
# 2 needed.
JEV_SKILL_ROUTING: bool = True
JEV_SKILL_THRESHOLD: float = 1.25
# Judge each Execution's design recommendations when it ends and keep the
# scores in its record. It reports only.
JEV_ASSESS_EXECUTIONS: bool = True
# Check what remote MCP servers return, and what the user writes, for text that
# tries to instruct the agent. A server's reply at or above the threshold is
# withheld from the Specialist; the user's own words are only flagged.
JEV_GUARDRAIL: bool = True
JEV_GUARDRAIL_THRESHOLD: float = 0.75
# Paths
BASE_DIR: Path = Path(__file__).resolve().parent.parent
def overlay_dirs(self) -> list[Path]:
return [
path if path.is_absolute() else self.BASE_DIR / path
for path in (
Path(entry.strip())
for entry in self.OVERLAY_SKILLS_DIRS.split(",")
if entry.strip()
)
]
def default_overlays(self) -> list[str]:
return [n.strip() for n in self.DEFAULT_OVERLAY_SKILLS.split(",") if n.strip()]
def terraform_plugin_cache(self) -> str | None:
"""The provider cache directory as an absolute path; None when disabled."""
if not self.TF_PLUGIN_CACHE_DIR.strip():