mirror of https://github.com/affaan-m/ECC.git synced 2026-08-28 18:59:47 +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recommendation reads as pinned to a superseded generation.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

1.4 KiB

Raw Permalink Blame History

inclusion, name, description

inclusion	name	description
auto	performance	Performance optimization guidelines including model selection strategy, context window management, and build troubleshooting

Performance Optimization

Model Selection Strategy

Claude 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

Claude Sonnet 5 (Best coding model):

Main development work
Orchestrating multi-agent workflows
Complex coding tasks

Claude 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

Extended thinking is enabled by default in Kiro, reserving tokens for internal reasoning.

For complex tasks requiring deep reasoning:

Ensure extended thinking is enabled
Use structured approach for planning
Use multiple critique rounds for thorough analysis
Use sub-agents for diverse perspectives

Build Troubleshooting

If build fails:

Use build-error-resolver agent
Analyze error messages
Fix incrementally
Verify after each fix

1.4 KiB Raw Permalink Blame History