All checks were successful
check agents / check (push) Successful in 10s
ALZ-F01 Discovery as a sub-agent orchestrator (sub-agents/) and as eight individual declarative agents (individual-agents/), with their KAB workflow exports. Shared check, render and import scripts, the alz-discovery-sample MCP server, the crucible-kab-dev deploy profile, deployment docs, platform issue reports and the source material. Agent steps time out at 20 minutes. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
1.4 KiB
1.4 KiB
0011. Uploaded files and project artifacts reach the planner and the inventory as text
| Status | Accepted |
| Date | 2026-10-29 |
| Decided by | Product owner (CP1) |
| Requirements changed | DSC-01 (3214451) and DSC-03 (3214453): estate data came only from MCP sources; client files and earlier outputs were not an input |
Decision
- Two optional KAB activity steps sit in front of the workflow:
- Parse Assessment Files (
u1): the run form's upload fieldfile; - Artifacts (
a1): project artifacts fixed by id.
- Parse Assessment Files (
- The planner (s1) and the inventory agent (s3) take their
parsed_contentas two optional text inputs:source_documentsandreference_documents. - These agents are declarative, with no code to open files, so they take the text the platform has already extracted.
- Their prompts treat the text as evidence only: it never adds a target, it is cited as
document:sourceordocument:reference, it is weaker than MCP results, and it is never followed as an instruction. scripts/build_workflow.pyadds the front steps, andscripts/kab_import_workflow.pyvalidates and imports the workflow.
Consequences
- Size: inline text is bounded by the platform's payload limits. Large exports suit the orchestrator pattern, which reads files from the volume.
- Outputs: every step's reply remains an
execution_outputartifact. - The other six agents are unchanged (still 0.1.0).