This is the structural prep PR for the runtime-brief diet roadmap on
MUL-3560 — split out from the per-section compression work so the
refactor risk and the content-gating risk land separately.
Output is byte-for-byte identical to the pre-refactor monolithic
builder for every existing test fixture. All existing tests pass
unchanged. The follow-up PR (0.6) will start gating sections per the
Section × Kind matrix from Eve's design comment on MUL-3560 (drop
Mentions / Comment Formatting / Issue Metadata / Sub-issue out of
quick-create, drop Comment Formatting / Mentions / Attachments out of
autopilot and chat, etc.), with negative assertions added alongside
each removal so each kind's brief contract becomes machine-checked.
What changed:
- runtime_config_kind.go (new): taskKind enum + classifyTask helper.
Five kinds, mutually exclusive in practice; the documented
precedence rule keeps the tiebreak deterministic even if a future
caller breaks the mutex by accident. hasIssueContext is the
predicate Issue Metadata and Sub-issue Creation gate on.
- runtime_config_sections.go (new): every section of the brief is
extracted into its own writeXxx helper, preserving byte sequences
exactly. Helpers with internal conditions keep those conditions;
helpers the dispatcher always wants to call are unconditional.
- runtime_config.go: buildMetaSkillContent collapses from a
~450-line monolith to a ~70-line dispatcher — prelude, conditional
context sections, a 5-way kind switch over Workflow bodies, and
trailing sections. The matrix of "which kind gets which section"
is now readable in one screen.
- runtime_config_kind_test.go (new): TestClassifyTask covers all 5
kinds plus tiebreak cases; TestTaskKindHasIssueContext pins the
predicate semantics; TestBuildMetaSkillContentKindMatrix is the
structural canary that locks today's per-kind section set so any
later PR that drops a section from a kind must update its
expectations in lockstep.
Verification:
- go build ./... ok
- go vet ./internal/daemon/... ok
- go test ./internal/daemon/... ./internal/handler/... ok
- go test ./internal/daemon/execenv -run TestClassifyTask -v pass
- go test ./internal/daemon/execenv -run TestTaskKindHasIssueContext pass
- go test ./internal/daemon/execenv -run TestBuildMetaSkillContent pass
No production behaviour change in this PR. No new logging, no new
char-bucket fields — those are in PR #4439 and compose cleanly with
this refactor.
Co-authored-by: multica-agent <github@multica.ai>
