* remove claude tool use backwards compatability
* remove anthropic tool use from mistal-format
* further simplify mistral-format
* fix linting error in unrelated file
* welcome page now shows login button
* adding cline apikey to context
* added cline provider + making sure welcome page closes
* adjusting welcome page language
* swapped cline provider to use openai flavor requests
* handling credit limit errors (super hacky ugh)
* welcome view hiding api options by default
* added back account page and relying more heavily on the firebase custom token to ensure persistent login
* persisting login state through window reloads
* renaming Account -> Cline Account
* use openrouter format with cline api
* Update welcome experience
* Fix error handling
* added generation details tracking to cline provider
* small edit to account view
* logging cline instead of openrouter
* logging cline instead of openrouter
* response.data instead of response.data.data
* set isdev to false for prerelease
* changeset added
* Update tricky-zebras-talk.md
* Update tricky-zebras-talk.md
* welcome page language
* more logging and updated authentication system to be more robust and reliable
* only removing custom token on explicit log out action
* even more aggressive custom token fetching + storing in apiConfig
* moving firebase auth logic to webview because nodejs firebase token refresh is not supported
* cleaned up all old logic for extension server side auth persistence
* reconciling merge conflicts with main
* reconciling merge conflicts
* package-lock.json
* package lock
* package-lock
* packagejson + lock
* use standard API Request Failed title for all API errors while maintaining detailed credit limit information in error content
* deleting packagejson line for vertexai
* reverting package-lock changes
* package-lock.json straight from main
* removing redundant csp allowance
* Fix package-lock
* Add missing options to cline stream
* Remove duplicate csp
* Remove email subscribe
* Update welcome page and cline account view
* Fixes
* Fix errors
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
* rebased to main
* Added files from patch
* restored ClineProvider call to Migration deletes, added try try catch
* Restored changes to Cline.ts
* Updated tests
* Updated tests, prettier
* Optimize commit operation
* Fixed branch deletion, cleanup
* Cleanup
* minor cleanuop
* changeset
* Fix checkpoint tracker initial commit not tracking any files
* Ensure we are getting hash from branch and not main
* Revert first commit logic
* Change to get the correct hash for 'See new changes' on new and resumed tasks
* Make checkpoints commits async
* Update .changeset/cold-beers-laugh.md
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* updated service with specific events
* added telemetry to understand task creation and tool usage and task completion
* updated the telemetry system to track system messages and user messages
* added better message counting telemetry
* removed a create task which was suppose to be a restart
* updated so we can detect task completion properly
* switched to production key
* added changeset
* Modify telemetry signatures
* Fixes
* remove redundant task created
* Update src/services/telemetry/TelemetryService.ts
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Clean up apiconfiguration
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Co-authored-by: Dennis Bartlett <bartlett.dc.1@gmail.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* 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
Saoud Rizwan