Skip to content

Feature adapt copaw - #6

Merged
guima-why merged 3 commits into
mainfrom
feature_adapt_copaw
May 15, 2026
Merged

Feature adapt copaw#6
guima-why merged 3 commits into
mainfrom
feature_adapt_copaw

Conversation

@guima-why

Copy link
Copy Markdown
Collaborator

No description provided.

guima-why and others added 3 commits May 15, 2026 14:48
Covers two phased goals:
- Phase 1: Provider Registry refactor + QwenPaw zero-config LLM source + existing provider model list updates
- Phase 2: 12+ new native providers (Gemini, Kimi, MiniMax, ZhiPu, Volcengine, etc.) + Anthropic active cache

Co-authored-by: Cursor <cursoragent@cursor.com>
- Remove cache_strategy from ProviderDescriptor (cache decisions are
  model-level, handled inside provider classes like
  DashScopeProvider._supports_explicit_cache)
- Remove supports_stream_options from descriptor (keep as class attr)
- Standardize provider constructor signatures: all accept
  (model, api_key, base_url, effort, provider_key)
- Document DeepSeekProvider base_url un-hardcoding
- Add existing provider constructor changes to Phase 1 file list
- Clarify _MODEL_PREFIX_TO_PROVIDER stays hand-written (not derived)
- Add zhipu codingplan variants

Co-authored-by: Cursor <cursoragent@cursor.com>
@guima-why
guima-why force-pushed the feature_adapt_copaw branch from e836061 to 8d15e25 Compare May 15, 2026 10:05
@guima-why
guima-why merged commit 95fb353 into main May 15, 2026
10 checks passed
@guima-why
guima-why deleted the feature_adapt_copaw branch May 20, 2026 08:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant