Claude/main gpt oss work 011 c ux nnof g1 y az5 kiib5ae z #999
Conversation
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
μλ‘μ΄ GPT OSS 20B λͺ¨λΈμ λν λ¬Έμ νμΌμ μΆκ°νμ΅λλ€.
π μ»€λ° μκ°: 2025. 11. 09. 22:13:47
π λ³κ²½ ν΅κ³:
β’ μ΄ νμΌ: 1κ°
π μΆκ°λ νμΌ:
+ README.gpt-oss-20b.md
π§ ν¨μ λ³κ²½ λ΄μ©:
π README.gpt-oss-20b.md (mdνμΌ):
β
Added: Customizations(), Optimizations(), Features()
π§ μ£Όμ λ³κ²½ λ΄μ©:
β’ κ°λ° λ¬Έμ λ° κ°μ΄λ κ°μ
Integrates GPT-OSS-20B as a supported model while maintaining full backward compatibility with existing Qwen-Coder models. Key Changes: - Added GPT-OSS-20B model constants and 128K token limit configuration - Implemented reasoning_content parsing for both streaming and non-streaming - Added comprehensive environment configuration and security guidelines - Optimized timeout settings for lower-end GPU hardware Features: - Parallel model support (GPT-OSS-20B + Qwen-Coder) - reasoning_content transparency feature support - Graceful degradation for non-GPT-OSS-20B models - Zero breaking changes, fully backward compatible Files Modified: - packages/core/src/config/models.ts (+2 lines) - packages/core/src/core/tokenLimits.ts (+1 line) - packages/core/src/core/openaiContentGenerator/converter.ts (+20 lines) Documentation: - docs-optrader/00-SUMMARY.md - Executive summary and quick start - docs-optrader/01-api-test-results.md - Comprehensive API testing - docs-optrader/02-phase1-configuration.md - Configuration changes - docs-optrader/03-phase2-core-changes.md - Core implementation details - docs-optrader/04-environment-configuration.md - Setup and security guide Testing: - API tests: β Complete (chat, tool calling, streaming) - Build verification: β Success - Integration tests: β³ Pending manual validation Performance: - Default timeout increased recommendation: 300s (for slow GPUs) - Token limit: 128K context window - Generation speed: ~60 tokens/sec (GPU dependent) Security: - No hardcoded API keys - Environment variable based configuration - Comprehensive security best practices documented Ref: README.gpt-oss-20b.md
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
TLDR
Dive Deeper
Reviewer Test Plan
Testing Matrix
Linked issues / bugs