mirror of https://github.com/affaan-m/ECC.git synced 2026-08-17 21:15:40 +02:00

Files

T

fd1b11cfc7 docs: refresh model-selection guidance to the Claude 5 families (#2723 )

Model-routing guidance across the rules, skills, and harness-steering docs
still recommends Sonnet 4.6 / Opus 4.5-4.6 by name. Readers on the current
generation have to map those onto Sonnet 5 / Opus 5 themselves, and the
recommendation reads as pinned to a superseded generation.

Renames the recommended models in guidance tables and updates two pinned
model IDs in code samples:

- rules/steering guidance: .cursor, .kiro, and the seven translated
  performance.md copies (ja-JP, zh-CN, zh-TW, ko-KR, pt-BR, es, tr)
- skills/prompt-optimizer complexity-routing table (+ zh-CN copy)
- skills/cost-aware-llm-pipeline MODEL_SONNET constant (+ zh-CN, ja-JP)
- docs/examples project-guidelines template, which pinned the invalid ID
  claude-sonnet-4-5-20250514 (+ zh-TW, ja-JP copies)

Deliberately left alone:

- The "Pricing Reference (2025-2026)" table in cost-aware-llm-pipeline.
  Renaming those rows while keeping the existing per-token figures would
  assert Claude 5 pricing this change has not verified.
- Executable model config (.opencode/opencode.json, agent.yaml). Those pins
  change real agent behavior and belong in their own reviewed change.
- Historical and illustrative references: the-shortform-guide session
  transcripts, the ECC-PRO roadmap log entry, gan-style-harness's
  "Opus 4.5-class"/"Opus 4.6-class" capability tiers, and
  strategic-compact's deliberately generic "400k Opus 4.x" example.
- docs/ATLAS-CLOUD-GUIDE.md, which lists a third-party provider's catalog.

Documentation wording only; no behavioral change.

Co-authored-by: Phumchai Tanonsi <274848436+phumchai1515-prog@users.noreply.github.com>

2026-08-11 19:36:48 -04:00

1.0 KiB

Raw Blame History

效能優化

模型選擇策略

Haiku 4.5（Sonnet 90% 能力，3 倍成本節省）：

頻繁呼叫的輕量 agents
配對程式設計和程式碼產生
多 agent 系統中的 worker agents

Sonnet 5（最佳程式碼模型）：

主要開發工作
協調多 agent 工作流程
複雜程式碼任務

Opus 5（最深度推理）：

複雜架構決策
最大推理需求
研究和分析任務

上下文視窗管理

避免在上下文視窗的最後 20% 進行：

大規模重構
跨多個檔案的功能實作
除錯複雜互動

較低上下文敏感度任務：

單檔案編輯
獨立工具建立
文件更新
簡單 Bug 修復

Ultrathink + Plan 模式

對於需要深度推理的複雜任務：

使用 ultrathink 增強思考
啟用 Plan 模式 以結構化方法
用多輪批評「預熱引擎」
使用分角色子 agents 進行多元分析

建置疑難排解

如果建置失敗：

使用 build-error-resolver Agent
分析錯誤訊息
增量修復
每次修復後驗證

1.0 KiB Raw Blame History Unescape Escape