* enhance provider store and execute flow
* replace provider settings with store-driven UI
* hook dropdown components to provider store
* Fix ChatGPT and Claude input injection for new tab providers
* fix <inpute serach box query>
* make snapshot cache only 100ms TTL
* ollama: replace localhost with 127.0.0.1 as it works better
* fix: Plan generator in custom agent fixed
* wip: limited context mode
* limited context: remove goal mode
* limited context mode in planner too
* simple log token usage and emit
* adding logging in invokeWithRetry
- Extend ProviderSchema with autoSubmit, openIn, submitKey, focusBeforeSubmit flags
- Update ChatGPT and Claude providers with auto-submit configuration
- Centralize auto-submit logic in executeProviderAction using chrome.browserOS.sendKeys
- Simplify CommandInput by removing duplicate provider handling
- Enables easy scaling for future providers (Perplexity, Grok, etc.)
Fixes: ChatGPT and Claude now automatically send Enter after query is pasted
Follows CEO specification: get tab ID + send Enter via chrome.browserOS API
* Newagent: Add missing tools - MCP, group tabs, get seelected tabs
* deleting: PoCAgent and ReactLoopImpl
* Newagent; Adding MCP prompt
* NewAgent: glow animation added
* newagent: show pointer anitmation for element click, type and clear too
* pointer timeout 3s
* wip: new predefined mode
* CLEAN-UP: moved back to singleton architecture
* fix: prevent sending PROHIBITED tags
* NewAgent: predefined planner implemented
* Minor: renaming for better readability
* Fix: Newtab pre-defined plan execution
* predefined planner, added MCP to prompt
* Fix manifest.json version
* predefined planner also gets reasoning history; commented TODO for executor
* minor: rename
* Browsercontext: enable snapshot cache again with 1s TTL
* Langchain remove: llm cache
* langchain provider: properly read vision
* supportsVision moved to executionContext and using that in new agent
* PocAgent + refactor (#77)
* Screenshot tool fixed
* ReactAgent loop
ReactAgent loop
v0.2
* Trim to max tokens implemented correctly
trim max tokens
* JSON Parse fix
Fixed json.parse
* Minor fix -- add system message always at position 0
* minor fix
* Added support for passing screenshot size to captureScreenshot
backup
* Make react agent use screenshot tool
* Refactor backend and execution (#75)
* wip: new exection class and manager
* wip: new pubsub channels
* wip: new background handlers
* new execution logic
* removed execution status
* handle workflow status for processing in sidepanel
* mcp server fix
* sending pause message
* better portName parsing, sidepanel sends tabId, storing tabId too
* 49.0.0.26 release
* docs: OmkarBansod02 signed the CLA in browseros-ai/BrowserOS-agent#$pullRequestNo
* Refactor backend and execution (#75)
* wip: new exection class and manager
* wip: new pubsub channels
* wip: new background handlers
* new execution logic
* removed execution status
* handle workflow status for processing in sidepanel
* mcp server fix
* sending pause message
* better portName parsing, sidepanel sends tabId, storing tabId too
* Moved react agent into POCAgent
* Revert changes of ReacStrategy from BrowserAgent
* Minor fix
* fix: execution class abort issue
* clean-up: removed un-used MessageTypes
* clean-up: execution-manager simplified
* better abort handling
---------
Co-authored-by: Felarof <nithin.sonti@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Screenshot failure handling
* fixes to custom agent -> sidepanel
* fix: portName stable
* fix: pause/reset + newtab connector
* New agent: wip-1
* fix: JSONify message content in MessageManagerReadyOnly
* disable cacheLLM and fixing image type detection
* new agent: wip-2
* rename: <BrowserState> as <browser-state> and <SystemReminder> as <system-reminder>
* new-agent: wip-3
---------
Co-authored-by: Felarof <nithin.sonti@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* implement validator eval
* implement online eval foundation
* further implementing online evals
* enhance evaluation data logging
* implement LLM scoring, remove redundant EventEnricher
* cleanup
* fix build errs from merging, extend LLM scorer context
* settled evaluation framework
* update evals documentation
* fix evals screenshots
* fix typos
* Evals config moved to env variables and tested
* test
* Update manifest to 49.1
* Removed duplciate + button
* Just use previous way of registering tools as that is not required for evals
* Add claude commands for research, plan and implement
* evals2 research and plan
implementation plan
new implementation plan
* Evals2 implementation
test test
* Removed old eval hooks
Remove old evals hooks
* evals 2 added to env
* Eval2 enhancement plan
backup
* Make Braintrust project configurable
Make Braintrust project configurable
* Enhanced scorer -- using Gemini 2.5 pro for evaluation
backup v0.1
enhancement v0.2
v0.2
backup v0.3
backup v0.4
* Deleted old evals directory
* Clean up old evals code
* Bunch of fixes and improvements
backup
fixes 0.1
more fixes
fixes
more elaborate prompts
braintrust logger fix
* Renamed files
backup
