busya
d874a4dca6
Add prototype/openapi/validate/resume commands, wire edge-failure matrix into UX, enforce traceability + validation gates, mandate C4/C5 belief-runtime verification. Rework 038-dashboard-scenario-model artifacts: applicability, structured edge cases, 24-class UX state matrix, interactive HTML prototype, standardized OpenAPI 3.1 (7 ops), full RTM with coverage gate, 56-task backlog, and PASS validation report.
105 lines
6.5 KiB
Markdown
105 lines
6.5 KiB
Markdown
---
|
|
description: Execute the implementation plan by processing the active tasks.md for the superset-tools repository (Python backend + Svelte frontend).
|
|
handoffs:
|
|
- label: Audit & Verify (Tester)
|
|
agent: qa-tester
|
|
prompt: Perform semantic audit, executable verification, and contract checks for the completed task batch.
|
|
send: true
|
|
- label: Orchestration Control
|
|
agent: swarm-master
|
|
prompt: Review tester feedback and coordinate next steps.
|
|
send: true
|
|
---
|
|
|
|
## User Input
|
|
|
|
```text
|
|
$ARGUMENTS
|
|
```
|
|
|
|
You **MUST** consider the user input before proceeding (if not empty).
|
|
|
|
## Outline
|
|
|
|
1. **Preflight Gate — `/speckit.validate` must PASS and be current**: Before any implementation work, run `.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` and locate `FEATURE_DIR/validation.md`. Abort if it does not exist, has status `BLOCKED`, or is older than any validated input (`spec.md`, `plan.md`, `tasks.md`, `traceability.md`, `contracts/modules.md`, `contracts/openapi.yaml`, or applicable UX/prototype artifacts). Report: "Validation gate missing, blocked, or stale. Run `/speckit.validate` and resolve all blocking findings before `/speckit.implement`." Proceed only when the report says `PASS` and records fingerprints or timestamps matching the current artifacts.
|
|
2. If `checklists/` exists, evaluate checklist completion status before implementation proceeds.
|
|
3. Load implementation context from:
|
|
- `tasks.md`
|
|
- `plan.md`
|
|
- `spec.md`
|
|
- `ux_reference.md`
|
|
- `validation.md` — preflight gate report (must show PASS)
|
|
- `contracts/modules.md` when present
|
|
- `contracts/openapi.yaml` when present
|
|
- `research.md`, `data-model.md`, `quickstart.md` when present
|
|
- `traceability.md` — for story → task → test mapping
|
|
- `.specify/memory/constitution.md`
|
|
- `README.md`
|
|
- relevant `docs/adr/*.md`
|
|
4. Parse tasks by phase, dependencies, story ownership, and guardrails.
|
|
5. Execute implementation phase-by-phase with strict semantic and verification discipline.
|
|
|
|
## Repository Reality Rules
|
|
|
|
- Source paths: `backend/src/**/*.py` and `frontend/src/**/*.svelte`.
|
|
- Active feature docs always live under `specs/<feature>/...` and are discovered via the `.specify/scripts/bash/*` helpers.
|
|
- Default verification stack (all timeout-protected via root Makefile):
|
|
- `make test-unit` — backend unit tests (SQLite, <120s)
|
|
- `make test-frontend` — frontend vitest tests
|
|
- `make lint` — ruff + eslint
|
|
- `cd frontend && npm run build` — production build check
|
|
- `make coverage` — coverage reports (optional, run after tests pass)
|
|
- `make test-related F=path/to/changed_file.py` — smart selection for narrow scopes
|
|
- Do not fall back to Rust `cargo`/`src/server/` conventions — this is a Python/Svelte project.
|
|
|
|
## Semantic Execution Rules
|
|
|
|
- Preserve and extend canonical anchor regions.
|
|
- Match contract density to effective complexity.
|
|
- Keep accepted-path and rejected-path memory intact.
|
|
- Do not silently restore an ADR- or contract-rejected branch.
|
|
- For C4/C5 Python orchestration flows, account for the belief runtime (JSON structured logging via `reason()`, `reflect()`, `explore()`).
|
|
- For C4/C5 Svelte components, account for belief runtime (console markers `[ComponentID][MARKER]`).
|
|
- Treat pseudo-semantic markup as invalid.
|
|
|
|
### C4/C5 Belief Runtime Verification (MANDATORY)
|
|
|
|
After implementing any C4 or C5 contract, run BOTH static marker checks AND Axiom belief runtime audit:
|
|
|
|
1. **Static marker check** (per-file):
|
|
- Every C4/C5 `#region` contract MUST have `@RATIONALE` and `@REJECTED` tags. Missing tags → **BLOCKING** — do not proceed.
|
|
- For Python C4/C5 functions: verify `reason("...")` is called before mutation, `reflect("...")` is called after mutation, and `belief_scope(anchor_id)` context manager wraps stateful operations.
|
|
- For Svelte C4/C5 components: verify `[ComponentID][REASON]`, `[ComponentID][REFLECT]` console markers appear before and after state transitions respectively.
|
|
|
|
2. **Axiom belief runtime audit** (per phase):
|
|
- Invoke `axiom_audit({operation="audit_belief_runtime", workspace_path="/root/ss-tools", selection_mode="all"})` after implementing C4/C5 contracts.
|
|
- Invoke `axiom_audit({operation="audit_belief_protocol", workspace_path="/root/ss-tools", selection_mode="all"})` for decision-memory completeness.
|
|
- `audit_belief_runtime`: detects C4/C5 contracts that lack REASON/REFLECT/EXPLORE runtime markers.
|
|
- `audit_belief_protocol`: detects C4/C5 contracts missing `@RATIONALE`/`@REJECTED` decision memory.
|
|
- If either audit returns findings for contracts touched in the current phase → **BLOCKING** — reject missing instrumentation. Do NOT silently lower complexity to C3 to bypass.
|
|
- Run these audits BEFORE marking C4/C5 tasks complete.
|
|
|
|
3. **Rejection rule**: If a contract is structured at C4/C5 complexity but lacks runtime belief markers, it is incomplete. Do not mark the task complete. Add the missing instrumentation. Never silently downgrade complexity — the complexity tier describes what the contract IS, not what is convenient to implement.
|
|
|
|
4. **Test verification**: Tests for C4/C5 contracts MUST assert that belief markers are emitted. For Python: mock the logger and verify `reason()`, `reflect()` calls. For Svelte: spy on `console.debug` and verify marker format `[ComponentID][MARKER]`.
|
|
|
|
## Progress and Acceptance
|
|
|
|
- Preflight validation gate (`/speckit.validate`) must have PASS status before any implementation begins.
|
|
- Mark tasks complete only after local verification succeeds AND (for C4/C5) belief runtime audit passes.
|
|
- Handoff to the tester must include touched files, declared complexity, contract expectations, ADR guardrails, belief runtime audit results, and executed verifiers.
|
|
- Final acceptance requires explicit evidence that verification was executed.
|
|
- `.kilo/plans/*` may exist as internal assistant scratch context, but it is not part of the speckit feature output surface and must not replace `specs/<feature>/...` artifacts.
|
|
|
|
## Completion Gate
|
|
|
|
No task batch is complete if any of the following remain in the touched scope:
|
|
- broken or unclosed anchors
|
|
- missing complexity-required metadata
|
|
- unresolved critical contract gaps
|
|
- rejected-path regression
|
|
- required verification not executed
|
|
- **C4/C5 contracts lacking `@RATIONALE`/`@REJECTED` tags (belief protocol audit must PASS)**
|
|
- **C4/C5 contracts lacking REASON/REFLECT/EXPLORE runtime markers (belief runtime audit must PASS)**
|
|
- **Silent complexity downgrade to bypass instrumentation requirements**
|