Files
Jonathan Boniface e22d037ab0 ALZ-F02 Assessment: individual agents, intake, rate card input, critic fixes
- Six declarative agents generated from the v1.1 stories (scaffold_from_stories.py, ADR 0001),
  and a 9-step workflow export (build_workflow.py).
- Code-only intake (ADR 0008) verifies the one Discovery package in code before any agent.
- The rate card is the run input rate_card_document; no upload step (ADR 0009).
- Critic 0.1.6 after live runs on crucible-kab-dev:
  - K-12 model independence checked at build time against each agent's deployed model
    (ADR 0010); the critic reports it from its two inputs;
  - receives in_cloud_estate for K-10; an unverified K-10 never fails the run alone;
  - K-08 allows the scoring note to list findings as advisory, as ALZ-ASM-04 must;
  - carries ALZ-ASM-03's and ALZ-ASM-04's rule sections, copied by the scaffold, so it can
    recalculate risk, confidence and TCO.
- The scaffold refuses to regenerate unless every story file is present.
- Case azure-crucible-kab-dev-assessment with an illustrative rate card.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 22:13:25 +00:00

29 lines
1.5 KiB
Markdown

# CP1 - Assessment Intake Agent
Checks the Discovery package in code before Assessment starts (ADR 0008). Step `s0` of the workflow "CP1 - Agentic
Landing Zone - Assessment", after the parse step and before the planner. It answers from code (`app/intake.py`,
called by the `pre_process` hook): no model, no tools.
## What it checks
| Check | Refused when |
|---|---|
| One package | The selected artifacts hold no Discovery package, or more than one |
| Version | `package_version` isn't one it reads (`1.0`) |
| Integrity | A part the manifest lists is missing, or its `sha256` over the part's canonical JSON doesn't match |
| Completeness | The manifest isn't `complete` |
| Quality | The Discovery critic's verdict isn't `pass` |
| Provenance | The manifest's execution id isn't the run's `discovery_execution_id`, or its engagement isn't `engagement_id` |
A refusal fails the step with every reason, so the run stops before any Assessment agent reads Discovery. The
package is found at any depth in each parsed document, because KAB may wrap a step's output or hold it as a JSON
string.
## What it returns
`verified`, the package version, the Discovery execution and run ids, the critic's verdict, the provider, the parts
checked and those absent, the source gaps, the agent versions, Discovery's `applications` and `ungrouped_assets`
(F01 ADR 0021), the scorecard (F01 ADR 0020) and a one-line note.
Tests: `python3 -m pytest tests/` (no runtime needed), on the live package of Discovery run `exec_14956d524a8b`.