A new Deliverable in the packaging Phase, produced by a delivery planner
after validation.
- The planner writes the plan as data: work packages that name the Elements
they deliver, and activities with days, what each follows, and whether the
team or the customer owns it.
- Code checks the plan against the design: every Element belongs to a work
package, and the activities can be scheduled.
- Code computes the schedule, with no more of the team's activities at once
than the team has people, and the critical path.
- Code writes the WBS dictionary (a work package is done when the Checks on
its Elements pass), the activity sequence and a timeline on a relative axis
from Day 0.
- The plan is checked against the delivery window from the agreed scope; over
it, the Deliverable says by how much and names the critical path.
- With a start date it also gives calendar dates and a Mermaid Gantt chart.
- The timeline is added to the solution guide, and the plan's length is in
execution.json and the packaging Approval.
Not run with real models.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every Execution now begins by agreeing the scope, before requirements.
- A new Phase and Deliverable, produced by a scope analyst with two tools:
scope_read shows what is settled and what is not; scope_set records fields
with where each value came from (the request, the customer's answer, or an
assumption with its reason). Code checks each value against the catalogue.
- With someone present the analyst asks for what is missing; with nobody
present it assumes it, visibly. With no spec it drafts one from the request.
A value the customer stated in the file is changed only by their own answer.
- A submission cannot leave an essential field unknown. Code writes the
completed spec, the data every later Specialist reads, and the information
register, from what was recorded.
- The spec's status follows the Execution: under review, approved, then
locked as a Baseline. A Change request starts from the delivered scope.
- The requirements analyst derives from the agreed scope and no longer asks
for what it settles.
About 80 tests assumed requirements came first; tests/scoped.py runs scoping
ahead of a test's own script, and tests about order and counts are updated.
Not run with real models.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A scope spec is a YAML file of what the customer wants and the facts a design
depends on, complete or partly filled. It sits beside the Intent, which stays
in the customer's words.
- skills/scoping holds a provider-neutral catalogue of 63 fields; the Cloud
provider's bundle supplies the values it allows for the fields left to it.
- app/scope.py reads a spec against the catalogue with no model: it refuses an
unknown field or a value of the wrong type, and yields what is stated, what
is left to the agent, what is unknown and how pressing each gap is. A field
may say ask, decide or not_applicable.
- ExecutionEngine.start(scope=...), /generate, A2A metadata and evaluation
cases accept one. Its statement is the request, its engagement reference
names the Customer case, and its run options apply. A pre-approved start is
refused when an essential field is not settled.
- The spec as supplied is kept unaltered beside a completed copy with
assumptions, gaps, provenance, readiness and a status.
- Every Specialist is shown the spec and given the Skill: a stated choice
binds, exclusions are out of scope.
- Covers workloads and platform foundations; case-08-landing-zone starts from
a benchmark spec.
Plans for scoping (iteration 9) and the work breakdown structure (iteration
10, nothing built), and the design spec they come from. Not run with real
models.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A pillar's checklist item the request gives no information about was marked
"not addressed", which reads as a fault in the design. It is missing
information. The checklist review gains a fourth outcome, to confirm with the
customer, which must carry the question to ask. The questions are written
into the design recommendations and the guide, and to customer-questions.md;
the evaluation's judged check counts such an item as accounted for.
Records the owner's decisions of 2026-10-10 and the vendor's answers on Jev's
retention, training, context and rate limits (iteration 5 step 1), and the
owner's labels, which showed the judged question was wrong, not the judges.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The README now covers the router, Change requests, overlay Skills, Jev's
uses and the current layout. VALIDATION.md no longer points at the removed
root Terraform. ADR-0004 and ADR-0007 gain dated "As built" notes; ADR-0007's
says which uses of Jev send Deliverable content.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Accepted by the owner on 2026-10-08 with its six decisions as written:
a person approves every lesson; a lesson must be shown to help by
evaluation; lessons are per Cloud provider; overlay Skills come only from
configured directories; each Execution records the Skills it loaded; and
lesson candidates are client data kept out of the repository.
- CONTEXT.md gains Lesson candidate, Lesson and Overlay Skill.
- Iteration 4 step 9 is complete; steps 10 and 12 name the decisions they
must meet and are unblocked. Neither is built.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
Record the direction and build plan for replacing the upstream
google-cloud-solution-architecture skill with a portable agent.
- ADR-0002: Agent Skills are the portable unit of behaviour, loaded by
the framework's native skill runtime; discovery and grounding use
each Cloud provider's hosted remote MCP servers.
- ADR-0003: LangGraph holds Execution state, checkpoints and
interrupts; a ReAct Orchestrator and Specialists run as ADK
LlmAgents with SkillToolset. Supersedes ADR-0001.
- CONTEXT.md: domain glossary (Execution, Phase, Approval, Revision,
Orchestrator, Specialist, Deliverable, Dependency, Cloud provider).
- .scratch/solution-architect-agent/spec.md: build spec with the
dependency graph, Revision rules, tool tiers, MCP allowlists, A2A
interaction, tests and nine build increments.
- .scratch/phase-pipeline/spec.md: superseded; kept as decision log.
- CLAUDE.md and docs/agents/: agent skill configuration (local
markdown issue tracker, triage labels, domain docs).
- README.md: direction note; flags current ADK classes as stubs.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>