# Model capability tiers for typed-pipeline routing.
#
# Each tier defines score floors (against model-registry/*.yaml `scores` dimensions).
# The CP picks the cheapest registry entry meeting ALL floors (MR-9/MR-11 — cheapest-wins).
#
# Stages that need a specific tier set `tier:` on their `kind: agent` node (W2).
# Until W2 lands, templates hardcode `model:` directly and these floors serve as
# documentation of the intended constraint.
#
# See claude/stage-routing.md for the authoritative pipeline stage map.

tiers:

  planning:
    description: >
      Judgment-heavy work: plan generation, spec re-draft (replan-spec-opus),
      architecture review escalation (review-spec-opus). Requires sustained
      reasoning over large context windows.
    min_scores:
      complexity: 9
      creativity: 9
      context_utilisation: 9
    qualifies_today:
      - deepseek-v4flash       # benchmark-inflated 9s; hold to allowed_models ceiling
      - minimax
      - claude-opus-4
    note: >
      WF-SCH-14 allowed_models ceiling remains authoritative until M7 observed-score
      recalibration corrects benchmark-inflated registry entries.

  spec-test:
    description: >
      Spec-adherent structured work: spec drafting, spec arch review, scope/decompose,
      test writing, impl review, merge verdict. Needs reliable spec adherence and
      test execution.
    min_scores:
      spec_adherence: 9
      test_pass_rate: 9
    qualifies_today:
      - minimax
      - claude-sonnet-4
      - claude-opus-4

  coding:
    description: >
      Narrow TDD implementation against pre-validated tests. Lower floors because
      tests already constrain the solution space.
    min_scores:
      spec_adherence: 7
      test_pass_rate: 7
    qualifies_today:
      - airouter-qwen3
      - airouter-deepseekv4flash
      - minimax
      - claude-sonnet-4
      - claude-opus-4