Workflow Router

Workflow Router

Goal

Map an instructor request to exactly one workflow in workflows/*/workflow-spec.json, with explicit rationale and fallback behavior.

Inputs

• Instructor request (free text)
• Optional mission.json
• Repository workflow inventory under workflows/

Produce

Write routing-decision.json with:

• request_summary
• candidate_workflows (ranked)
• selected_workflow
• selected_reason
• confidence (high|medium|low)
• required_skills
• optional_skills_selected
• skip_conditions_applied
• human_confirmation_required (bool)
• fallback_workflow

Selection policy

1. Discover candidates by reading all workflow-spec.json files.
2. Score candidates on:

• intent match (create, redesign, evaluate, validate, benchmark);
• artifact intent (exam/lab/course/project/grading/figures);
• constraints (language_mode, evaluation_mode, level, duration, toolchain);
• required input availability.

3. Select the highest score only if score gap to second candidate is significant.
4. If ambiguity remains, set human_confirmation_required: true.

Skill-chain policy

• Start from workflow execution_order.
• Apply skip_conditions if artifacts already exist and pass validators.
• Add optional skills only when their trigger in optional_extensions is satisfied.
• Never invent a skill not present in workflow spec.

Rules

• Do not use hardcoded workflow names in logic; load from repository each run.
• Emit one selected workflow, never multiple.
• If confidence is low, provide a fallback and require confirmation before generation.
• Keep routing deterministic for same inputs and same repository state.