2 Commits

Author	SHA1	Message	Date
Eve	03ee42982b	MUL-3560: gate runtime brief sections per task kind (PR 0.6) ... Builds on PR 0.5's helper extraction. The dispatcher now skips sections each task kind doesn't need, per Eve's Section × Kind matrix on MUL-3560. Measured impact (claude provider, full fixture with 2 repos + 10 skills, comparing PR 0.5 ↔ PR 0.6): kind PR 0.5 PR 0.6 Δ Δ% ------------------------------------------------------------ comment-triggered 19462 19462 0 0% assignment-triggered 18034 18034 0 0% autopilot-run-only 11174 8442 -2732 -24% quick-create 12497 4799 -7698 -62% chat 11155 8423 -2732 -24% ✓ comment / assignment unchanged this PR (their diet comes from the per-section compression PRs #1..#9 on the roadmap) ✓ quick-create from 12.5k → 4.8k chars (-62%) ✓ autopilot and chat from 11k → 8k chars (-24% each) The matrix encoded in `buildMetaSkillContent`: Section | comment | assign | autopilot | quick_create | chat ----------------------+---------+--------+-----------+--------------+------ Available Commands | full | full | full | minimal | full Comment Formatting | ✓ | ✓ | — | — | — Repositories | △ | △ | △ | — | △ Project Context | △ | △ | — | — | — Issue Metadata | ✓ | ✓ | — | — | — Instruction Precedence| — | ✓ | — | — | — Sub-issue Creation | ✓ | ✓ | — | — | — Skills | ✓ | ✓ | ✓ | — | ✓ Mentions | ✓ | ✓ | — | — | — Attachments | ✓ | ✓ | — | — | — What changed: - runtime_config.go: the dispatcher now decides per kind which helpers to call. Always-on prelude unchanged. The matrix above is documented inline on `buildMetaSkillContent` and is the single source of truth. - runtime_config_sections.go: new `writeAvailableCommandsQuickCreate` helper — emits only the `issue create` line plus the `multica --help` escape hatch (~500 chars vs ~4400 for the full variant). Used only when classifyTask returns kindQuickCreate. - runtime_config_kind.go: `hasIssueContext` doc comment narrowed to the three real call sites (Project Context, Issue Metadata, Sub-issue Creation) per GPT-Boy's PR 0.5 review nit. - runtime_config_kind_test.go: * TestBuildMetaSkillContentKindMatrix updated to encode the new expected section set per kind. Heading match tightened so it only fires on the heading line, not inline references like "See ## Comment Formatting below" inside Available Commands. * TestBuildMetaSkillContentQuickCreateAvailableCommands (new) locks the minimal-variant content: `issue create` is present, every other Core command — get / status / metadata / comment add / children / repo checkout / squad — is asserted absent. - execenv_test.go: TestInjectRuntimeConfigIssueMetadataSectionScope now expects the metadata Core discovery lines to be ABSENT for quick-create (it uses the minimal Available Commands) and PRESENT for every other kind. Comment narrowed to match. Verification: - go vet ./internal/daemon/... ok - go test ./internal/daemon/... ./internal/handler/... ok Backwards compatibility: - InjectRuntimeConfig signature unchanged (still 2-tuple). - No new daemon flags, no new ctx fields, no per-provider changes. - Reverting this commit restores PR 0.5 byte-for-byte; the change is contained inside buildMetaSkillContent's section selection. Risk and follow-up: - comment-triggered and assignment-triggered still ~19k each; their reduction lands in PRs #1 (Available Commands compression), #4 (Mentions compression), #5 (Issue Metadata compression). - The full Available Commands variant retains "See ## Comment Formatting below" as an inline reference, which is now a dangling pointer for autopilot/chat where Comment Formatting is gated out. Cleanup deferred to PR #1 of the roadmap (Available Commands compression) — addressing it requires kind-specific Available Commands variants, which is exactly that PR's surface. Co-authored-by: multica-agent <github@multica.ai>	2026-06-23 14:48:24 +08:00
Eve	38aa864e70	MUL-3560: refactor buildMetaSkillContent into kind-driven dispatcher ... 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>	2026-06-23 14:33:42 +08:00