Commit Graph

7 Commits

Author SHA1 Message Date
Paul O'Reilly
350c0eeed4 feat(templates): 6-tier escalation ladder — add MiniMax + Fable tiers
New tiers in the coding queue:
  airouter(0-2) → minimax(3-5) → sonnet(6-7) → opus(8-9) → fable(10) → blocked(11+)

- models/claude-fable-5.yaml: Fable 5 model definition (Anthropic cloud, claude runner)
- harnesses/composites/code-fable-tdd-repo/v1: Fable TDD composite (mirrors opus, anthropic-cloud-paul-oauth auth)
- model-registry/harness-roles.yaml: claude-fable-5 → code-fable-tdd-repo under code-tdd role
- model-registry/tiers.yaml: claude-fable-5 added to coding.qualifies_today
- task-templates/workflow/minimax-impl-ready@1.yaml: MiniMax TDD workflow (scope: 3 files / 200 lines / 30m)
- task-templates/workflow/fable-impl-ready@1.yaml: Fable TDD workflow (scope: 5 files / 400 lines / 60m)

Claude-Session: https://claude.ai/code/session_015sCpoFee3LsLKbHQ4FRRWY
2026-07-29 01:59:54 +12:00
Paul O'Reilly
1da98eb708 Add model-registry/harness-roles.yaml — W3 harness auto-selection role table 2026-07-12 23:17:07 +12:00
Paul O'Reilly
78229c5dba feat(routing): add tiers.yaml + rename spec/review-arch templates to airouter
W1 stage-routing work:
- model-registry/tiers.yaml: defines planning/spec-test/coding tier floors
  (complexity≥9/creativity≥9/context≥9 | spec_adherence≥9/test_pass_rate≥9 |
  spec_adherence≥7/test_pass_rate≥7) with qualifies_today lists
- spec-draft-airouter@2.yaml: honest name for what was spec-draft-opus@1
  (always ran Qwen3.6/airouter, not Opus)
- review-spec-arch-airouter@1.yaml: honest name for review-spec-arch-opus@1

Old @1 files kept for in-flight task backward-compatibility.

Claude-Session: https://claude.ai/code/session_01B35bPAKv5uyW1F9gzMcRN7
2026-07-12 19:03:51 +12:00
Paul O'Reilly
8167035b6b Add DeepSeek V4 Flash model and coder composite via airouter
- models/airouter-deepseekv4flash.yaml: DeepSeek-V4-Flash on airouter.ch endpoint,
  temp 1.0 / top_p 1.0 per recommended reasoning defaults, 262k context / 65k output
- model-registry/airouter-deepseekv4flash.yaml: deepseek provider, complexity 9,
  creativity 9, cost_efficiency 10 (covered by airouter sub)
- harnesses/contexts/deepseek-code-methodology/v1: DeepSeek-specific methodology
  CLAUDE.md; same rules as qwen-code-methodology but with correct model header
- harnesses/composites/code-airouter-deepseekv4flash-repo/v1: coder composite
  using airouter/v1 context (shared endpoint + secret — no new ESO resources needed)
2026-06-23 22:07:33 +12:00
Paul O'Reilly
906de0954d Add minimax model registry entry; rename tdd-impl workflow
- minimax.yaml: scores copied from Opus (placeholder until real benchmark),
  cost 0.0/0.0 (subscription), provider=minimax. Now auto-selectable by
  min_scores routing (smart-agent at complexity≥9 will reach it).
- tdd-impl → write-code-following-tdd (name field updated)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-28 17:12:06 +12:00
Paul O'Reilly
2b3e4a3e80 feat(model-registry): add provider field to all entries
Add optional provider field (anthropic, openai, alibaba, github,
openrouter, opencode) as groundwork for F-WE-PDIV provider diversity
enforcement in auto-model selection.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-28 13:40:56 +12:00
Paul O'Reilly
37a5165dfb init: seed framework reference content from agent-runtimes main repo 2026-04-26 12:17:42 +12:00