Design is now approved before any infrastructure code is written (ADR-0005). A new target-architect Specialist produces one graph of Elements, Relationships and Checks; the diagram is rendered from it, deployment guidance must account for every Check, and validation gives a verdict per Check. Requirements, components, products and recommendations carry ids in data files, and a submission with a gap in the Requirements chain is refused. Also in this commit: - Customer cases group Executions, with an intent history per case - lesson candidates are captured when an Execution ends - evaluation gains chain, verdict, judged and interactive checks, and per-case thresholds - Terraform providers are cached between checks - the requirements analyst proposes defaults instead of asking - the legacy-baseline case and the checks that only read it are removed - ADR-0006 (Change requests) accepted; ADR-0004 and ADR-0007 proposed - plans for iterations 4 to 7 under .agents/plans/ Unproven with a real model: no evaluation run has completed on this design. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2.8 KiB
2.8 KiB
Step 15 — Implementation Detail
- Customer case is a glossary term (
CONTEXT.md): a caller-supplied slug grouping the Executions for one customer workload. An Execution started without one belongs tounassigned, so every Execution sits under a case. - Layout.
deliverables/cases/<customer_case>/executions/<execution_id>/holds an Execution's files.execution_dir,case_dirandlessons_fileinapp/states/execution_state.pyare the only places these paths are built. execution.jsonin each Execution folder names the case, the Execution, the Session, the Workflow request, and for each Deliverable its document and attachments.intent/in each case folder records the customer's Intent and its history (app/customer_case.py). Each Workflow request is written as given tointent/001.md,002.mdand so on when its Execution starts.intent/history.jsonlists every statement in order with the Execution it started, that Execution's status (in_progress,completed,completed_with_warnings) and the path to its files. This replaced thecase.jsonindex first built for this step;execution.jsoncarriesintent_version.- Lesson candidates are grouped the same way:
lessons/candidates/<customer_case>/<execution_id>.json, and the record carriescustomer_case. - Callers.
ExecutionEngine.start(customer_case=...);/generatetakescustomer_casein its body and answers 400 for an unsafe one; A2A readscustomer_casefrom the message metadata. The evaluation uses each benchmark case's id. - The case id must be 1 to 64 lowercase letters, digits or hyphens, starting and ending with a letter or digit. It becomes a directory name, so anything else is refused before the Execution starts.
- Existing content moved.
deliverables/as-is,target,validation,guidesand the 68 oldexecutionsfolders are now underdeliverables/cases/legacy-baseline/, with anintent/folder built from the request recorded in each old run'srequirements.md, ordered by file time.scripts/validate_artifacts.pyandtests/test_artifacts.pylook there.
Limits:
- An Execution that ends with warnings writes no Deliverable files (an existing rule). Its request is still in the Intent history, with its status and no path, and its lesson candidates are grouped under its case.
- The 68 old runs were asked 12 different things but share one case,
legacy-baseline. They can be split into a case per request fromintent/history.jsonif that matters. /generate's response keys are unchanged, so it does not return the case;execution.jsondoes.- The database rows carry the case only inside the status details, not as a column.
Tests: tests/execution/test_engine.py (grouping, manifest, index, unassigned, refused ids), tests/a2a/test_server.py (/generate), tests/execution/test_lessons.py.