daniel.w
/
opencode-cursor-agent
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases 2 Wiki Activity

feature/gemini-web-provider #1

Merged
daniel.w merged 16 commits from feature/gemini-web-provider into master 2026-04-02 18:36:51 +00:00
Conversation 0 Commits 16 Files Changed 21 +2317 -147
daniel.w commented 2026-04-02 18:36:36 +00:00
Owner
Copy Link
No description provided.
daniel.w added 16 commits 2026-04-02 18:36:37 +00:00
33a0e53709 feat: Add GeminiWeb provider foundation 
- Add Provider interface and factory pattern
- Create apitypes package for shared types
- Implement GeminiWeb provider with:
  - Browser automation using Rod
  - Session pool management
  - Cookie persistence
  - DOM interaction for Gemini web interface
- Add gemini-login command for session setup
- Add CURSOR_BRIDGE_PROVIDER env variable

Remaining: Integration with chat.go handlers
df22640d6a feat: Add Gemini provider env vars to Makefile and CLI options 
- Add PROVIDER, GEMINI_ACCOUNT_DIR, GEMINI_BROWSER_VISIBLE, GEMINI_MAX_SESSIONS to Makefile
- Update gemini-login command to support --visible flag
- Add help text showing env vars and usage examples
- Display session save location and browser visibility on startup
f33353897c feat: Add provider display in startup logs and OpenCode gemini-web config 
- Add provider name display in LogServerStart (cursor/gemini-web)
- Show gemini-dir and max-sess when using gemini-web provider
- Update Makefile to include gemini-web provider in opencode.json
- Update opencode-models to sync models for both cursor and gemini-web
- Add Gemini Web Provider examples in help text
19985dd476 feat: Route chat completions to Gemini Web provider when configured 
- Add HandleGeminiChatCompletions for Gemini Web provider requests
- Update router to route requests based on cfg.Provider
- Support both streaming and non-streaming modes for Gemini
- Map stream chunks to OpenAI-compatible SSE format
69df57555d fix: Improve Gemini Web DOM selectors and add debug output 
- Make model selector optional (skip if not found, use current model)
- Add multiple fallback selectors for input field and send button
- Add debug logging to trace execution flow
- Improve error messages to suggest running gemini-login
9f41d3b5b5 feat: Allow using Gemini Web without login 
- Remove requirement to login before using Gemini Web
- If logged in (cookies exist), use the account
- If not logged in, continue without login (browser opens)
- When browser is visible, prompt user they can login or continue without
- Save cookies only if user actually logs in
24459ffcfe fix: Don't wait for user input during login flow 
- Remove blocking 'Press Enter' prompt
- Continue without waiting when no session exists
- Save cookies asynchronously if user logs in during session
- Add debug output for finding input field and send button
- Try Enter key as fallback for sending message
32673c028e refactor: Complete rewrite of GeminiWeb provider 
Based on project-golem implementation:

Phase 1: Browser Persistence
- Add BrowserManager singleton to manage browser lifecycle
- Use launchPersistentContext with UserDataDir
- Auto-save cookies and session state
- Clean Chrome lock files on startup
- Single browser instance reused across requests

Phase 2: Improved DOM Interaction
- Use correct input selectors (ProseMirror first)
- Implement 'Physical Enter' send method
- Trigger input/change/keyup events properly
- Check for 'Stop' button to detect busy state

Phase 3: Session Management
- No manual cookie saving/loading needed
- Session pool just manages userDataDir paths
- Default session directory structure

Breaking changes:
- Remove manual cookie management
- Browser stays open between requests
- Simpler session management
3d5f2d91c0 feat: Switch to playwright-go for better DOM automation 
Major refactor using Playwright (pure Go):
- Add playwright-go dependency (v0.5700.1)
- Create PlaywrightProvider with auto-wait for elements
- Use LaunchPersistentContext for session persistence
- Implement Locator-based element finding (auto-wait)
- Fill input using Playwright's built-in methods
- Add fallback selectors for input fields
- Better error messages with page URL and title

Key improvements over Rod:
- Auto-wait for elements (solves 'input field not found')
- More mature browser automation library
- Better documentation and examples
- Based on project-golem's proven strategies

Installation:
- Playwright driver and Chromium downloaded to ~/Library/Caches/ms-playwright/
- ~160MB download (one-time setup)
104e55d613 fix: Add proper page ready check before finding input 
Key improvements:
- Wait for page to fully load (SPA needs time)
- Wait for input field to be visible before typing
- Check login status only after page is ready
- Add fallback wait (3 seconds) if first attempt fails
- Properly handle error messages

Based on project-golem's PageInteractor.waitForReady()
bef521504e feat: Add debug mode with screenshot and page analysis 
Features:
- Wait for user ENTER in visible mode (GEMINI_BROWSER_VISIBLE=true)
- Save screenshot to /tmp/gemini-debug.png
- Save HTML to /tmp/gemini-debug.html
- JavaScript-based element detection
- Multi-strategy wait (A: selectors, B: time, C: JS, D: debug)
- Detailed logging of each strategy attempt
- Page structure dump in debug mode

This helps identify why input field is not found
3fec6e55eb fix: Always save diagnostics on any error 
- Add saveDiagnostics method
- Use defer in Generate to catch all errors
- Simplify typeInput error handling
- Automatic screenshot and HTML dump on failure
4517b07f33 feat: Implement Gemini Web provider with model selection 
- Fix handler to use PlaywrightProvider instead of old Provider
- Add model selection for Gemini Web (fast/thinking/pro)
- Improve response extraction to remove 'Gemini said' prefix
- Add progress logging for headless mode
- Fix navigation to use Domcontentloaded instead of Networkidle
- Add proper input field selectors (.ql-editor)
- Improve response completion detection with stability check
daniel.w merged commit 85f695250e into master 2026-04-02 18:36:51 +00:00
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels
No items
No Label
Milestone
Clear milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
No Assignees
1 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: daniel.w/opencode-cursor-agent#1
No description provided.
Delete Branch "feature/gemini-web-provider"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?