Integration of 3 quick wins into existing UOK infrastructure: 1. Model Learning (Quick Win #2) → metrics.js - Record outcomes to model-learner for per-task-type performance tracking - Hook: recordUnitOutcome() now calls ModelLearner.recordOutcome() - Fire-and-forget: never blocks outcome recording on learning failure - Enables adaptive model routing decisions in downstream gates 2. Self-Report Fixing (Quick Win #1) → triage-self-feedback.js - Auto-fix high-confidence reports (>0.85) in applyTriageReport() - Hook: After triage and requirement promotion, apply auto-fixes - Fire-and-forget: never blocks report application on fix failure - Returns reportsAutoFixed count for triage metrics 3. Knowledge Injection (Quick Win #3) → already integrated in auto-prompts.js - Already active in execute-task prompt template - Semantic matching with graceful degradation All integration points: - Fire-and-forget: learning/fixing failures never block dispatch - UOK-native: use existing outcome recording, db, gates - Backward compatible: applyTriageReport now async, but callers handle it - No new dependencies: all modules already in codebase Testing: 2934 tests pass (no regressions from integration) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
741 B
741 B
ADR-008 Implementation Plan
Related ADR: ADR-008-sf-tools-over-mcp-for-provider-parity.md Status: Rejected — never implement Date: 2026-04-09
Superseded Boundary
Never build or restore an SF MCP server package.
Current SF product boundary:
- SF uses MCP only as a client for external tool servers configured through
.mcp.jsonor.sf/mcp.json. - SF workflow execution runs through native SF tools, headless/RPC, and the daemon/RPC client path.
- SF never exposes its workflow as an MCP server for Claude Code, Cursor, or other external clients.
This document is kept only as a tombstone for the rejected implementation plan. Do not revive this direction.