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>
This commit is contained in:
2026-11-05 22:13:25 +00:00
parent 9e503885cc
commit e22d037ab0
153 changed files with 13004 additions and 0 deletions

View File

@@ -0,0 +1,20 @@
# Implementation plan: individual agents, ALZ-F02 Assessment & Disposition
For coding agents. Update the status in the same change as the work.
Status values: `done`, `blocked (<on whom>)`, `todo`.
| # | Step | Verified by | Status |
|---|---|---|---|
| 1 | Generate the six agent folders from the v1.1 story files (`scripts/scaffold_from_stories.py`) | `check_agents.py` (cp4's rules): 6 folders, 0 problems; 25 declared MCP tools all exist on the existing servers | done (2026-11-02) |
| 2 | Eval cases per agent: Meridian sample Discovery outputs, `timeout: 330` | `python -m kyndryl_agent_runtime.eval --validate` | todo: locally, every schema is valid JSON Schema and every case input fits its input schema (2026-11-02); not yet run through the runtime's validator, or live |
| 3 | Workflow export: `u1`, `a1`, `p1` and six agent steps, `from_steps` hand-offs, critic approval | `build_workflow.py` asserts every field on both sides: 9 steps, 22 connections | done (2026-11-02) |
| 4 | Docs: README, ADRs 0001–0007, per-agent user guides and context | Review | done (2026-11-02) |
| 5 | Deploy profile entries for the six agents, then render | `render_k8s.py` + `kustomize build`: 3 objects each; critic on `gpt-5.4` | done (2026-11-02) |
| 6 | Deploy and register the three discovery servers in the CP1 tenant. ALZ-ASM-02 and ALZ-ASM-05 can't start without all three (ADR 0007). `cloud-knowledge` was retired on 2026-11-04; guidance is on the discovery servers | Gateway lists them healthy | partly done (2026-11-02): all four servers run in `mcp-servers` at their current versions (azure-discovery 0.1.3, aws-discovery 0.1.1, gcp-discovery 0.1.2, cloud-knowledge 0.1.1). Registration, and whether the gateway accepts the changed tool schemas, still to confirm with a KAB token. Customer credentials need the Vault Service |
| 7 | Build and push the six images; store each `MCP_AGENT_API_KEY`; `kubectl diff -k`, then `apply -k` | Pods ready; agent cards served | todo (needs the user's approval for each cluster change) |
| 8 | Validate and import the workflow (`scripts/kab_import_workflow.py`) | `validate-json` accepts it | todo |
| 9 | Run on Meridian: Discovery `RUN-008` (approved, verdict `pass`), its artifact ids, the approval reference, and `workflows/cases/meridian-assessment/rate-card.json` | Every step completes; the critic step waits for approval | todo |
| 10 | Workflow case `meridian-assessment` with checks written before the run, scored like F01's `evaluate_workflow_run.py` | Scored run | todo |
| 11 | Confirm the parsed Discovery text in a live run: the `---` separator, `file_metadata` names and order, and what happens when an output is too large to inline | `p1` output inspected | todo |
| 12 | Intake step `s0` (ADR 0008): `cp1-assessment-intake-agent` 0.1.0 checks the Discovery package in code (one package, sha256 per part, complete, critic pass, named run and engagement); the planner waits for it; one artifact selected | `tests/test_intake.py` 9 passed on the live package of `exec_14956d524a8b`; workflow export 10 steps | in progress (2026-11-05): all seven built, deployed and registered in the agent catalog; MCP keys for ASM-02 and ASM-05 stored (expire 2026-12-05); workflow imported as `wf_7b6cae08-327d-4ae4-875b-5ef7d044834f`; first run `exec_20d55cfe6fd7` stopped at the intake: the uploaded rate card reached `p1` (ADR 0009). Rate card moved to a run input; planner, disposition and critic 0.1.1 |