* Add retries to bedrock createMessage
Add retries to Bedrock's createMessage as indicated by [this](https://github.com/cline/cline/pull/1605#issuecomment-2665904349)
Similar to [this comment](https://github.com/cline/cline/pull/1605#issuecomment-2666290702) I am also experiencing a 429 every once in a while. Measuring a before/after, it's about a 90% improvement when there's no prompt caching. I'm going to add some logging and see if I can track it down further but honestly this is probably worth it as is.
* Add changeset
* Add Bedrock prompt caching support (optional)
This feature protected under checkbox because it is not yet rolled out
to everyone, and if you will try to send cache headers, and its not
enabled for you, you will get error
* Add changeset
* Update supported models
* Fix copy
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* Extract reuseable ModelDescriptionMarkdown from OpenRouter model picker
* Requesty: Add model picker component
* Refactor readOpenRouterModels to allow any dynamic list filename
* Extract parsePrice to allow reuse by other providers
* Simplify model display name switch case
* Requesty: Add dynamic model list fetching from API
* Requesty: Add default model selection
* Requesty: Specify max_tokens when sending request
* Add changeset
---------
Co-authored-by: Dennis Bartlett <bartlett.dc.1@gmail.com>
* Add OpenAI compatible cost calculation
* Requesty: Prepare for correct price calculation
* Native OpenAI: Update model caching info
According to [OpenAI's
website](https://platform.openai.com/docs/guides/prompt-caching),
gpt-4o, gpt-4o-mini, o1-preview and o1-mini support caching.
For gpt-4o, even though gpt-4o-2024-05-13 and
chatgpt-4o-latest do no support caching, users will see there are no
cached tokens, which will help avoid confusion.
* Native OpenAI: Call getModel once
* Native OpenAI: Extract yield usage into method
* Native OpenAI: Add caching and cost info to task header
* DeepSeek: Add cost info to task header
* Add changeset
**Branch-Per-Task:** Each repo now has a single Shadow Git repo, with separate branches per task (instead of one Shadow Git repo per task).
- **Legacy Support:** Existing Checkpoints remain functional, while all new Checkpoints use branch-per-task.
- **Commits:** Legacy tasks commit to legacy Checkpoints; new tasks commit using branch-per-task.
- **Diffing & Deletions:** Both legacy and branch-per-task Checkpoints support diffing and deletion.
No migration needed—existing tasks stay as-is, and new tasks adopt **branch-per-task** automatically.
* Initial webview vite migration
* Make vite work
* Fix test running
* Enable HMR, disable vite chunking
* Silence type checking errors
* Vite doesn't use browserslist
* get rid of breaking css flag
* add doc to getHMRHtmlContent
* Make it work
* Changeset
* Add IS_DEV to env definitions
* Update tasks to include HMR
* Update CSP image rules
* prettier
* reintroduce IS_DEV in env
* add new deps to pkg lock
---------
Co-authored-by: Dennis Bartlett <bartlett.dc.1@gmail.com>
* showing images after mcp responses
* images now open in a webview tab
* Open Graph link metadata display for MCP responses
* almost totally working rich mcp response display with images and embeds
* closer
* header for response display
* updated styling of mcp responses
* default to plain text if rich response is loading
* formatting fix
* added changeset output
* remove some old code
* add the dashed border back
* avoid XSS attacks by sanitizing the preview image urls and embeds
* remove incorrect vendor prefix css
* delete old version of open image implementation
* undo some comment removals and cleanups to make PR easier to read
---------
Co-authored-by: Andrei Edell <andrei@nugbase.com>
* feat(vertex): Add prompt caching support for Claude on Vertex AI
* Remove countTokens update claude 3.7
* claude-3-7-sonnet@20250219 support in Vertex AI as default model
