refactor: multi-provider LLM routing - GPT-5.5/Sonnet 4.6/Gemini 3.1#98
Closed
fukukei23 wants to merge 1 commit into
Closed
refactor: multi-provider LLM routing - GPT-5.5/Sonnet 4.6/Gemini 3.1#98fukukei23 wants to merge 1 commit into
fukukei23 wants to merge 1 commit into
Conversation
…i 3.1 Replace GLM/MiniMax-only routing with multi-provider architecture: - Quality tier: GPT-5.5 (code generation), Sonnet 4.6 (review/design), Gemini 3.1 Pro (secondary analysis) - Lightweight tier: GLM-5.1 (general/chat), MiniMax M2.7 (analytical) - Enable all 8 provider classes in provider factory - Update routing policy to recognize openai/anthropic/google vendors - Add 9 profile registry entries replacing old GLM-4-Plus profiles - Update task model map with quality/lightweight tier assignments - Update docs (README, SRS, architecture, roadmap, codex manifest) - Update tests for multi-provider assertions (100 passed) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits. |
fukukei23
force-pushed
the
refactor/d-task-multi-provider-llm
branch
from
2167ba8 to
0c01c54
Compare
Owner
Author
|
Closing: main has diverged significantly (92+ commits of refactoring). Merge conflicts in most files. Will re-implement needed tests on current main when NexusCore becomes active again. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
変更ファイル（14 files, +505/-386）
コア（5ファイル）
providers/__init__.py,provider_factory.py,routing_policy.py— プロバイダー有効化llm_profiles.py— 9プロファイル登録（GLM-4-Plus→GLM-5.1更新、glm_codex/glm_nano廃止）task_model_map.py— 品質/軽量ティアのタスク振り分けドキュメント（5ファイル）
テスト・設定（4ファイル）
test_llm_profiles_comprehensive.py,test_task_model_map_comprehensive.pyconfig.py,.env.templateTest plan
profile_to_model_name()で正しくvendor:model形式に変換される🤖 Generated with Claude Code