- Report (cp1-assessment-report-agent 0.2.0, step s7): a model writes the Assessment report from facts worked out in code (register, gaps, scorecard, rule traces, checks, and what each application is from the Discovery package); code sets the verdict and renders the pages. The disposition_signoff review point moves from the critic to the report. - Package (cp1-assessment-package-agent 0.1.1, step s8): after sign-off, every step's output in one package, with a register, a gaps register, the sign-off record, lineage and a sha256 per part, in code. Page step s9. - scripts/kab_register_agents.py: registers deployed agents in KAB's agent catalog (an in-place workflow update doesn't). - Runs exec_1b1257380df7 (014) and exec_374d5d577077 (015) completed on crucible-kab-dev: critic pass, report figures all in its facts, package complete with every digest recomputing. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2.5 KiB
CP1 - Assessment Package Agent
Assembles the Assessment package (ADR 0014), the hand-off that Strategy (F03), the Business Case (F04), Target
Architecture (F05) and Wave Planning (F06) select. Step s8 of the workflow "CP1 - Agentic Landing Zone - Assessment",
after the disposition_signoff review point (on the report, s7), so a package exists only for a run the Engagement Lead continued. It
answers from code (app/package.py, called by the pre_process hook): no model, no tools.
What it returns
| Part | From | Holds |
|---|---|---|
manifest |
all | engagement, run, execution id, critic verdict; the Discovery run, its package's artifact id and the intake's verification; the rate card's id and sha256; the models; each agent's version; the sign-off record; a sha256 and item count per part; complete and problems; the scorecard |
discovery |
s0 intake | the Discovery package as verified: run, version, critic verdict, provider, parts, source gaps, agent versions |
plan |
s1 | preconditions, applications, tasks, coverage gaps, rate card id, in_cloud_estate |
profiles |
s2 | readiness profiles and gaps |
risk |
s3 | scores and the high-risk tail |
security |
s4 | status, posture score, controls, findings, pillars (advisory) |
dispositions |
s5 | dispositions with rule trace, confidence workings, TCO and licensing |
critic |
s6 | verdict, checks, rejected dispositions, sign-off queue, unverified claims |
report |
s7 | the Assessment report's Markdown, as the Engagement Lead signed off from it (ADR 0015) |
register |
in code | one row per application: disposition, confidence, sign-off, risk, cost, findings, evidence |
gaps |
in code | what Assessment had to do without, per application, and the Discovery source that would fill it |
Sign-off (ADR 0014): continuing at disposition_signoff signs off the queue as it stands. Each register row's
signoff is signed_off (it was in the critic's queue), not_required, rejected, not_disposed, or
not_signed_off when the verdict wasn't pass. The next workflow records the approval as its run input
assessment_approval_ref.
Complete only when every copied part is present, the critic's verdict is pass and the intake verified the
Discovery package. Each part's sha256 is over its canonical JSON (sort_keys, separators=(",", ":"), UTF-8), as
in Discovery's package, so a consumer can recompute it before trusting the part.
Tests: python3 -m pytest tests/ (no runtime needed), on the step outputs of run exec_49e355141382.