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

@@ -31,7 +31,7 @@ from pathlib import Path
from typing import Any
from app.adk.runtime import AgentRuntime, AgentTask, Outcome, RoleSpec, ToolSpec
from app.agent import ExecutionEngine, Interaction, open_assembly
from app.agent import ExecutionEngine, Interaction, open_assembly, skill_dirs
from app.config import Settings, get_settings
from app.nodes.execution_nodes import automatic_reply
from app.recorder import InMemoryRecorder
@@ -131,6 +131,7 @@ async def run_with_scripted_user(
customer_case=case.id,
allow_cloud_read=False,
execution_id=execution_id,
overlay_skills=case.overlay_skills,
)
for _ in range(max_user_turns):
if interaction.status != "awaiting_user" or interaction.prompt is None:
@@ -150,7 +151,7 @@ async def run_case(
bundle = load_provider(settings.CLOUD_PROVIDER)
adk_runtime = AdkAgentRuntime(
skill_dirs={name: meta.path for name, meta in bundle.skills.items()},
skill_dirs=skill_dirs(settings, bundle),
model_timeout_seconds=settings.MODEL_TIMEOUT_SECONDS,
)
started = time.monotonic()
@@ -192,6 +193,7 @@ async def run_case(
allow_cloud_read=False,
execution_id=f"{execution_id}-base",
scripted_answers=case.scripted_answers,
overlay_skills=case.overlay_skills,
)
baseline_tokens = token_report(adk_runtime.usage)["total"].get("total")
baseline_seconds = round(time.monotonic() - started, 1)
@@ -205,6 +207,7 @@ async def run_case(
allow_cloud_read=False,
execution_id=execution_id,
scripted_answers=case.scripted_answers,
overlay_skills=case.overlay_skills,
baseline=base.execution_id,
)
elif case.interactive:
@@ -219,6 +222,7 @@ async def run_case(
allow_cloud_read=False,
execution_id=execution_id,
scripted_answers=case.scripted_answers,
overlay_skills=case.overlay_skills,
)
elapsed = time.monotonic() - started
write_progress()