Commit graph

10 commits

Author SHA1 Message Date
tanzhenxin
d67206819a fix(contextWindowSize): fix context window size update on model switch and ACP agent config priority
- Fix contextWindowSize not updating when switching models via setModel()
- Fix ACP agent to respect provider-configured contextWindowSize before auto-detection
- Simplify getTruncateToolOutputThreshold to use static threshold
- Add support for GLM-4.7, Kimi-2.5, and MiniMax-M2.1 models
- Update context usage display to require explicit contextWindowSize

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
2026-01-29 20:51:03 +08:00
xwj02155382
f9db8d5a73 refactor: improve config consistency and token limits
- Remove legacy childKey field from settingsSchema

- Add contextWindowSize and maxOutputTokens to documentation

- Refactor ContextUsageDisplay to accept contextWindowSize directly instead of Config object

- Add useMemo optimization for contextWindowSize in Footer component

- Fix logic gaps in contentGenerator for contextWindowSize and maxOutputTokens initialization

- Increase DEFAULT_OUTPUT_TOKEN_LIMIT from 4K to 8K for better usability

- Add fallback to default values when model is not available
2026-01-26 10:26:44 +08:00
xwj02155382
3bd460a9cc refactor: optimize token limit handling and simplify API
- Initialize contextWindowSize and maxOutputTokens in contentGeneratorConfig during config resolution
- Remove third parameter from tokenLimit() function for cleaner API
- Replace all tokenLimit() calls with direct config property access for better performance
- Add maxOutputTokens field to ContentGeneratorConfig type
- Update dashscope provider to use config.maxOutputTokens
- Auto-detect token limits from model during initialization if not user-configured
- Update settingsSchema: set contextWindowSize default to undefined and showInDialog to false

Benefits:
- Token limits calculated once during initialization instead of repeatedly
- Cleaner API with fewer parameters
- Better performance by caching computed values
- User configuration takes precedence over auto-detection
- All 72 unit tests passing
2026-01-23 16:27:10 +08:00
xwj02155382
4ad4aab3fd Merge branch 'main' into feature/add-context-window-size-config
Resolved conflicts in:
- packages/cli/src/ui/components/ContextUsageDisplay.tsx
- packages/cli/src/ui/components/Footer.tsx
- packages/cli/src/ui/components/Footer.test.tsx
- docs/users/configuration/settings.md

Changes:
- Merged main branch UI improvements with rightItems architecture
- Updated contextWindowSize documentation to be more concise
- Preserved all main branch features and functionality
2026-01-23 14:41:59 +08:00
xwj02155382
a684f07ff4 refactor: move contextWindowSize to ContentGeneratorConfig
- Add contextWindowSize field to ContentGeneratorConfig interface
- Update tokenLimit function to accept contentGeneratorConfig parameter
- Implement priority logic: user config > auto-detection
- Update chatCompressionService to use new API via getContentGeneratorConfig()
- Add contextWindowSize to MODEL_GENERATION_CONFIG_FIELDS for config resolution
- Add contextWindowSize to CLI settings schema (model.generationConfig)
- Update UI components (Footer, ContextUsageDisplay) to use new config API
- Fix test mocks to include getContentGeneratorConfig method

This refactor avoids modifying 71+ test files by moving the config
to the generator level instead of the Config class level.

Modified files:
- packages/core/src/core/contentGenerator.ts
- packages/core/src/core/tokenLimits.ts
- packages/core/src/services/chatCompressionService.ts
- packages/core/src/services/chatCompressionService.test.ts
- packages/core/src/models/constants.ts
- packages/cli/src/config/settingsSchema.ts
- packages/cli/src/ui/components/ContextUsageDisplay.tsx
- packages/cli/src/ui/components/Footer.tsx
2026-01-19 14:21:05 +08:00
tanzhenxin
5c6c3b2cf6 hide context usage if no request sent 2026-01-16 14:03:20 +08:00
tanzhenxin
b804b1f48a feat: Redesign CLI welcome screen and improve visual consistency 2026-01-16 11:48:31 +08:00
tanzhenxin
eb95c131be
Sync upstream Gemini-CLI v0.8.2 (#838) 2025-10-23 09:27:04 +08:00
tanzhenxin
7dbc240847 chore: sync gemini-cli v0.1.19 2025-08-18 19:55:46 +08:00
Pyush Sinha
8e6a565adb
fix: re render context usage indicator (#5102) 2025-08-07 18:16:47 +00:00