Skills suchen.../

Routing Policy Change | Skills Pool

Skill-Datei

Routing Policy Change

Modifies routing policy after signal extraction, including matched-decision logic, candidate-model selection, and downstream looper behavior. Use when changing decision predicates, thresholds, priorities, model ranking, cost or latency routing, or other post-signal routing policy.

vllm-project3,727 Sterne26.03.2026

Beruf
Kategorien: Machine Learning

Skill-Inhalt

Trigger

Change boolean decision logic after signal extraction
Change candidate-model selection, ranking, cost routing, or latency routing
Change looper behavior that belongs to matched-decision policy instead of signal extraction or plugin hooks

Workflow

Read change surfaces, module boundaries, and the Go router playbook for routing-policy context
Modify decision predicates, downstream model selection, or matched-decision looper behavior
Run make agent-report ENV=cpu CHANGED_FILES="..." to identify impacted surfaces
Run make agent-ci-gate CHANGED_FILES="..." to validate all affected constraints
Verify routing-policy behavior is covered by targeted tests and affected E2E expectations

Gotchas

Keep signal extraction upstream; do not smuggle classifier changes into this primary unless the signal contract itself is changing.
Keep plugin hooks separate; looper changes that only support matched-decision policy belong here, but request or response body plugins still belong to the plugin flow.

Verwandte Skills

Schnellinstallation

Routing Policy Change

npx skills add vllm-project/semantic-router

Skill herunterladen Repository öffnen

Autor: vllm-project
Sterne: 3,727
Aktualisiert: 26.03.2026
Beruf

Auf dieser Seite

Decision predicates and candidate-model ranking can change user-visible routing even when the patch looks small, so they are not refactors by default.

Must Read

docs/agent/change-surfaces.md
docs/agent/module-boundaries.md
docs/agent/playbooks/go-router.md

Standard Commands

make agent-report ENV=cpu CHANGED_FILES="..."
make agent-ci-gate CHANGED_FILES="..."
make agent-feature-gate ENV=cpu CHANGED_FILES="..."

Acceptance

Decision predicates and downstream candidate-model selection stay aligned with the same routing-policy intent
Targeted tests and affected E2E coverage are updated when routing-policy behavior changes
Routing-policy logic stays downstream of signal extraction and separate from plugin-only processing

02

Workflow

05Standard Commands

Softwareentwickler

Machine Learning

Continuous Learning V2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

Machine Learning

Continuous Learning V2

Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi. v2.1 çapraz proje kontaminasyonunu önlemek için proje kapsamlı instinct'ler ekler.

Machine Learning

Continuous Learning V2

훅을 통해 세션을 관찰하고, 신뢰도 점수가 있는 원자적 본능을 생성하며, 이를 스킬/명령어/에이전트로 진화시키는 본능 기반 학습 시스템. v2.1에서는 프로젝트 간 오염을 방지하기 위한 프로젝트 범위 본능이 추가되었습니다.

Machine Learning

Continuous Learning

Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。

Machine Learning

Continuous Learning

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Machine Learning

Pytorch Patterns

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

Softwareentwickler