* feat(api): add gemini-2.5-flash-preview-05-20 model configuration
* feat(tests): update apiModelId to gemini-2.5-flash-preview-05-20 in ProviderSettingsManager tests in case the old version is deprecated
* chore: add changeset
* feat(api): update vertexModels to add gemini-2.5-flash-preview-05-20 variants
* chore: update changeset
* [Condense] Add a button to condense the task context
* wip
* wip
* wip
* bring back delete size
* account for the system prompt in the context
* update tests to use systemPrompt
* add type
* translations
* nit
* update tests
* filter to the current task
* nit
* refactor
* nit
* non interactive option
* simplify chat summary UI
* changeset
* nit
* fix check-types
* throw
* feat(settings): Introduce the "auto-approve request count" feature from Cline
This is the first minor UI feature I've added, so please let me know if I'm missing anything! (translations, organization, etc!)
Please see commits for details
introduce allowedMaxRequests to globalSettingsSchema
update ExtensionState and its context with allowedMaxRequests
implement UI for setting max requests in AutoApproveMenu component
prompt user when auto-approval limit is reached with i18n support
increment consecutiveAutoApprovedRequestsCount and reset upon user approval
add translations for auto-approved request limit reached prompt in multiple languages
add new UI for "auto_approval_max_req_reached" in ChatRowContent
display prompt with title, description, and button for user action
🔧 chore(gitignore): add .idea to .gitignore to exclude IDE-specific files
- remove .idea/workspace.xml to clean up repository
* 🔧 chore(gitignore): add IDE configuration files to ignore list
- add .idea directory to ignore JetBrains IDE configurations
* 🌐 i18n(chat): add translation keys for api request limit
- introduce translation keys for "title" and "unlimited" in multiple languages
- update description for api request limit in various languages
* 🌐 i18n(chat): migrate auto-approved request limit translations
- move translations from common.json to chat.json across locales
- update component to use Trans for dynamic text rendering
* Update the UI for setting max requests
* Hide the auto-approve limit warning once clicked
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* Add Qwen3 model series to the Chutes provider
New models for the Chutes provider:
- Qwen/Qwen3-235B-A22B
- Qwen/Qwen3-32B
- Qwen/Qwen3-30B-A3B
- Qwen/Qwen3-14B
- Qwen/Qwen3-8B
* add changeset
The description for the `new_task` tool has been simplified for clarity.
Additionally, the example modes listed for the `mode` parameter have been updated to include "debug" instead of "ask".
This commit refines the custom instructions for the 'ask' mode. The changes aim to provide clearer guidance to the AI, emphasizing thoroughness in answering questions and caution against prematurely switching to code implementation.
Specifically, the instructions were updated as follows:
- Changed "Make sure to answer the user's questions" to "Always answer the user’s questions thoroughly"
- Changed "don't rush to switch to implementing code" to "do not switch to implementing code unless explicitly requested by the user"
- Changed "Include Mermaid diagrams if they help make your response clearer" to "Include Mermaid diagrams when they clarify your response"
These changes are reflected in both [`src/shared/modes.ts`](src/shared/modes.ts:80) and its corresponding snapshot file [`src/core/prompts/__tests__/__snapshots__/system.test.ts.snap`](src/core/prompts/__tests__/__snapshots__/system.test.ts.snap:5458).
