mirror of
https://github.com/affaan-m/ECC.git
synced 2026-09-18 15:50:25 +02:00
fd1b11cfc7
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the current generation have to map those onto Sonnet 5 / Opus 5 themselves, and the recommendation reads as pinned to a superseded generation.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>
60 lines
1.7 KiB
Markdown
60 lines
1.7 KiB
Markdown
---
|
|
description: "Performance: model selection, context management, build troubleshooting"
|
|
alwaysApply: true
|
|
---
|
|
# Performance Optimization
|
|
|
|
## Model Selection Strategy
|
|
|
|
**Haiku 4.5** (90% of Sonnet capability, 3x cost savings):
|
|
- Lightweight agents with frequent invocation
|
|
- Pair programming and code generation
|
|
- Worker agents in multi-agent systems
|
|
|
|
**Sonnet 5** (Best coding model):
|
|
- Main development work
|
|
- Orchestrating multi-agent workflows
|
|
- Complex coding tasks
|
|
|
|
**Opus 5** (Deepest reasoning):
|
|
- Complex architectural decisions
|
|
- Maximum reasoning requirements
|
|
- Research and analysis tasks
|
|
|
|
## Context Window Management
|
|
|
|
Avoid last 20% of context window for:
|
|
- Large-scale refactoring
|
|
- Feature implementation spanning multiple files
|
|
- Debugging complex interactions
|
|
|
|
Lower context sensitivity tasks:
|
|
- Single-file edits
|
|
- Independent utility creation
|
|
- Documentation updates
|
|
- Simple bug fixes
|
|
|
|
## Extended Thinking + Plan Mode
|
|
|
|
Extended thinking is enabled by default, reserving up to 31,999 tokens for internal reasoning.
|
|
|
|
Control extended thinking via:
|
|
- **Toggle**: Option+T (macOS) / Alt+T (Windows/Linux)
|
|
- **Config**: Set `alwaysThinkingEnabled` in `~/.claude/settings.json`
|
|
- **Budget cap**: `export MAX_THINKING_TOKENS=10000` (bash) or `$env:MAX_THINKING_TOKENS = "10000"` (PowerShell)
|
|
- **Verbose mode**: Ctrl+O to see thinking output
|
|
|
|
For complex tasks requiring deep reasoning:
|
|
1. Ensure extended thinking is enabled (on by default)
|
|
2. Enable **Plan Mode** for structured approach
|
|
3. Use multiple critique rounds for thorough analysis
|
|
4. Use split role sub-agents for diverse perspectives
|
|
|
|
## Build Troubleshooting
|
|
|
|
If build fails:
|
|
1. Use **build-error-resolver** agent
|
|
2. Analyze error messages
|
|
3. Fix incrementally
|
|
4. Verify after each fix
|