Commit graph

20 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
tanzhenxin
1c5b74ebd9 Merge branch 'main' into pr-1539 2026-01-29 19:18:23 +08:00
mingholy.lmh
2c9399f8e0 fix: use resolved authType to initialize ACP agent 2026-01-27 14:56:22 +08:00
xwj02155382
b5800eb823 refactor: remove redundant 'input' parameter in tokenLimit call
The tokenLimit function has a default parameter value of 'input' for the type parameter, so explicitly passing 'input' is redundant.
2026-01-26 13:39:45 +08:00
xwj02155382
8538f12689 fix: update contextWindowSize and maxOutputTokens when switching models
- Fix handleModelChange to update contextWindowSize and maxOutputTokens during hot-update
- Fix dashscope.ts to use contentGeneratorConfig.maxOutputTokens instead of tokenLimit()
- Fix acpAgent.ts to use model-specific contextLimit for each model
- Add comprehensive tests for model switching scenarios
- Fix all TypeScript type errors (index signature and ConfigSource types)
- Fix all ESLint errors (remove 'any' types)
2026-01-26 11:43:33 +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
LaZzyMan
a61a3c5680 Merge branch 'main' into feat/extension 2026-01-19 21:16:07 +08:00
tanzhenxin
1f1e78aa3b Refactor model handling in ACP agent and update auth error message
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
2026-01-17 10:53:57 +08:00
tanzhenxin
511269446f fix(acp): implement session/set_model method for JetBrains compatibility 2026-01-17 10:15:47 +08:00
LaZzyMan
551e546974 feat: move extension to core package 2026-01-14 15:30:27 +08:00
mingholy.lmh
2b511d0b83 fix: cold start issue and acp integration tests 2026-01-08 18:08:56 +08:00
LaZzyMan
74013bd8b2 feat: settings extension 2026-01-08 13:49:59 +08:00
mingholy.lmh
81de79c899 fix: best effort to use resolved authType/model across the repo 2026-01-08 12:11:23 +08:00
mingholy.lmh
8aceddffa2 feat: support /compress and /summary commands for non-interactive & ACP
integration
2025-12-26 17:55:02 +08:00
yiliang114
5cc01e5e09 feat(vscode-ide-companion): support context left 2025-12-25 23:51:50 +08:00
yiliang114
90bf101040 chore(vscode-ide-companion): simplify the implementation of context remaining 2025-12-24 14:29:25 +08:00
yiliang114
8e64c5acaf feat(vscode-ide-companion): support context left 2025-12-24 01:09:21 +08:00
tanzhenxin
0e6ebe85e4 test 2025-12-13 23:04:00 +08:00
tanzhenxin
4eb7aa5448 add acp authenticate update message 2025-12-13 12:01:46 +08:00
tanzhenxin
0a75d85ac9
Session-Level Conversation History Management (#1113) 2025-12-03 18:04:48 +08:00