Skip to content

feat: add Devin PR conflict resolver workflow#26624

Merged
keithwillcode merged 11 commits intomainfrom
devin/conflict-detection-workflow-1767974889
Jan 9, 2026
Merged

feat: add Devin PR conflict resolver workflow#26624
keithwillcode merged 11 commits intomainfrom
devin/conflict-detection-workflow-1767974889

Conversation

@keithwillcode
Copy link
Contributor

@keithwillcode keithwillcode commented Jan 9, 2026

What does this PR do?

Adds a GitHub Actions workflow that automatically detects PRs with merge conflicts and spins up Devin sessions to resolve them. This follows the same pattern established in #26618 (Cubic AI to Devin integration).

How it works:

  1. Triggers on push to main branch (when main updates could cause conflicts in open PRs)
  2. Also supports manual trigger via workflow_dispatch
  3. Uses GraphQL API to fetch all open PRs with their mergeable status, draft status, labels, and fork information in a single batched query (with pagination support)
  4. Skips draft PRs and PRs that already have the devin-conflict-resolution label
  5. For PRs with conflicts (mergeable === 'CONFLICTING'):
    • Creates a new Devin session with instructions to resolve conflicts
    • Adds the devin-conflict-resolution label to prevent duplicate sessions
    • Posts a comment on the PR with the Devin session link

Fork PR Support:

  • Detects PRs from external contributor forks via headRepository field
  • Only processes fork PRs where the contributor enabled "Allow edits from maintainers" (maintainerCanModify: true)
  • Provides fork-specific instructions to Devin: clone the fork repo, add upstream remote, fetch and merge from upstream

Updates since last revision

  • Added response.ok check before parsing Devin API response to properly handle HTTP error status codes (authentication errors, server errors) separately from successful responses that might be missing expected fields
  • Improved error logging to include the PR number for easier debugging when API calls fail

Mandatory Tasks (DO NOT REMOVE)

  • I have self-reviewed the code (A decent size PR without self-review might be rejected).
  • I have updated the developer docs in /docs if this PR makes changes that would require a documentation change. N/A - workflow only.
  • I confirm automated tests are in place that prove my fix is effective or that my feature works. N/A - GitHub Actions workflow, can be tested via manual trigger.

How should this be tested?

  1. Setup required: Ensure DEVIN_API_KEY secret is added to the repository (Settings → Secrets and variables → Actions)
  2. Manual test: Trigger the workflow manually via Actions → "Devin PR Conflict Resolver" → "Run workflow"
  3. Production test: Push a change to main that would cause conflicts in an open PR, verify the workflow detects it and creates a Devin session
  4. Draft PR test: Verify that draft PRs with conflicts are skipped (check workflow logs)
  5. Label test: Verify that PRs with the devin-conflict-resolution label are skipped
  6. Fork PR test: Verify that fork PRs with maintainerCanModify: true are processed with fork-specific instructions, and fork PRs without maintainer access are skipped

Human Review Checklist

  • Verify DEVIN_API_KEY secret exists in the repository
  • Consider if pagination (100 PRs per page) handles the repo's PR volume
  • Review duplicate detection logic - uses devin-conflict-resolution label
  • Verify the Devin prompt provides sufficient context for conflict resolution
  • Confirm the devin-conflict-resolution label will be auto-created or exists in the repo
  • Review fork handling logic - relies on maintainerCanModify flag from GitHub API
  • Verify fork-specific Devin instructions are correct (clone fork, add upstream, merge from upstream)

Link to Devin run: https://app.devin.ai/sessions/ca72c54a713e41a8a871a52a0a6d82c3
Requested by: @keithwillcode

Adds a GitHub Actions workflow that automatically detects PRs with merge
conflicts and spins up Devin sessions to resolve them.

How it works:
1. Triggers on push to main branch (when main updates could cause conflicts)
2. Also supports manual trigger via workflow_dispatch
3. Lists all open PRs and checks their mergeable status
4. For PRs with conflicts (mergeable=false, mergeable_state=dirty):
   - Checks if a Devin session was already created (avoids duplicates)
   - Creates a new Devin session with instructions to resolve conflicts
   - Posts a comment on the PR with the Devin session link

The workflow follows the same pattern as cubic-devin-review.yml for
consistency.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
@devin-ai-integration
Copy link
Contributor

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

  • Address comments on this PR that start with 'DevinAI' or '@devin'.
  • Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

  • Disable automatic comment and CI monitoring

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
@vercel
Copy link

vercel bot commented Jan 9, 2026

The latest updates on your projects. Learn more about Vercel for GitHub.

4 Skipped Deployments
Project Deployment Review Updated (UTC)
api-v2 Ignored Ignored Preview Jan 12, 2026 2:26pm
cal Ignored Ignored Jan 12, 2026 2:26pm
cal-companion Ignored Ignored Preview Jan 12, 2026 2:26pm
cal-eu Ignored Ignored Jan 12, 2026 2:26pm

Instead of filtering draft PRs in the loop, use the GitHub Search API
with 'draft:false' filter which is more efficient as it filters at the
API level rather than fetching all PRs and filtering locally.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
@keithwillcode keithwillcode self-assigned this Jan 9, 2026
@keithwillcode keithwillcode added this to the v6.1 milestone Jan 9, 2026
@keithwillcode keithwillcode marked this pull request as ready for review January 9, 2026 18:19
@keithwillcode keithwillcode requested a review from a team as a code owner January 9, 2026 18:19
@graphite-app graphite-app bot added core area: core, team members only foundation labels Jan 9, 2026
@keithwillcode
Copy link
Contributor Author

DevinAI, is this going to be able to handle conflicts on PRs that are forks from external contributors?

@devin-ai-integration
Copy link
Contributor

Good question. Currently, no - the workflow won't be able to resolve conflicts on PRs from external forks because:

  1. The prompt tells Devin to clone calcom/cal.com and push to the PR branch
  2. For fork PRs, the branch exists on the contributor's fork (e.g., contributor/cal.com)
  3. Devin wouldn't have write access to push to external contributors' forks

Options to handle this:

  1. Skip fork PRs - Add a check to skip PRs where headRepository.owner.login !== owner and just log that fork PRs need manual conflict resolution

  2. Use GitHub's "Allow edits from maintainers" - If the contributor enabled this option, maintainers can push to their fork branch. But this requires the contributor to have enabled it and uses a different git remote.

  3. Comment only for fork PRs - Instead of creating a Devin session, just post a comment asking the contributor to resolve conflicts themselves

I'd recommend option 1 (skip fork PRs) for now since it's the safest. Want me to implement that?

@keithwillcode keithwillcode marked this pull request as draft January 9, 2026 18:22
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
@devin-ai-integration
Copy link
Contributor

Implemented fork PR support:

  1. Updated GraphQL query to fetch headRepository (owner/name) and maintainerCanModify fields
  2. Fork PRs where the contributor enabled "Allow edits from maintainers" will be processed
  3. Fork PRs without maintainer access are skipped with a log message
  4. Devin gets fork-specific instructions: clone the fork repo, add upstream remote, fetch and merge from upstream

The workflow will now handle both regular PRs and fork PRs (when maintainer push access is enabled).

@keithwillcode keithwillcode marked this pull request as ready for review January 9, 2026 18:26
Copy link
Contributor

@cubic-dev-ai cubic-dev-ai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

1 issue found across 1 file

Prompt for AI agents (all issues)

Check if these issues are valid — if so, understand the root cause of each and fix them.


<file name=".github/workflows/devin-conflict-resolver.yml">

<violation number="1" location=".github/workflows/devin-conflict-resolver.yml:161">
P2: Check `response.ok` before parsing the response body to explicitly handle HTTP error status codes from the Devin API. This distinguishes API failures (authentication errors, server errors) from successful responses that might be missing expected fields.</violation>
</file>

Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.

@github-actions
Copy link
Contributor

github-actions bot commented Jan 9, 2026

Devin AI is addressing Cubic AI's review feedback

A Devin session has been created to address the issues identified by Cubic AI.

View Devin Session

Copy link
Contributor

@cubic-dev-ai cubic-dev-ai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

1 issue found across 1 file

Prompt for AI agents (all issues)

Check if these issues are valid — if so, understand the root cause of each and fix them.


<file name=".github/workflows/devin-conflict-resolver.yml">

<violation number="1" location=".github/workflows/devin-conflict-resolver.yml:190">
P2: Missing HTTP response status check before parsing Devin API response. If the API returns an error (4xx/5xx), the code will silently fail without logging the actual HTTP status. Check `response.ok` first to provide clearer error messages for debugging.</violation>
</file>

Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.

@github-actions
Copy link
Contributor

github-actions bot commented Jan 9, 2026

Devin AI is addressing Cubic AI's review feedback

A Devin session has been created to address the issues identified by Cubic AI.

View Devin Session

Address Cubic AI review feedback: Add response.ok check before parsing
the response body to explicitly handle HTTP error status codes from the
Devin API. This distinguishes API failures (authentication errors,
server errors) from successful responses that might be missing expected
fields.

Co-Authored-By: unknown <>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
@keithwillcode
Copy link
Contributor Author

DevinAI let's add a safety net of maximum 15 PRs to resolve conflicts on

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
@devin-ai-integration
Copy link
Contributor

Added a maximum 15 PRs safety net. If more than 15 PRs have conflicts, the workflow will only process the first 15 and log a warning message.

@keithwillcode keithwillcode enabled auto-merge (squash) January 9, 2026 18:54
Copy link
Contributor

@pedroccastro pedroccastro left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good to me! 🚀

@keithwillcode keithwillcode merged commit b367e15 into main Jan 9, 2026
107 of 113 checks passed
@keithwillcode keithwillcode deleted the devin/conflict-detection-workflow-1767974889 branch January 9, 2026 19:10
dhairyashiil added a commit that referenced this pull request Jan 10, 2026
* fix: skip stale run-ci label check on workflow re-runs (#26590)

* fix: trust community PRs when maintainer pushes to the branch

When a maintainer merges main into a community PR branch, the new SHA
invalidates the run-ci label timing check because the label was added
before the new push. This fix adds a check to trust the PR if the
person who pushed the latest commit has write access.

This handles the case where a maintainer:
- Merges main into a community PR to resolve conflicts
- Pushes any changes to help the contributor

The security model is maintained because:
- Only users with write access can trigger this trust
- The maintainer has reviewed the code by pushing to it

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* fix: skip stale label check on workflow re-runs

Instead of implicitly trusting maintainer pushes (which could be just
a sync action without code review), use github.run_attempt to detect
re-runs. If run_attempt > 1, it means the workflow was explicitly
re-triggered (via run-ci.yml or manual re-run), so we skip the stale
label check.

This avoids the need to remove and re-add the 'run-ci' label after
syncing a community PR with main, while keeping the explicit approval
flow intact.

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* Simplify comment about re-runs in PR workflow

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Keith Williams <keithwillcode@gmail.com>

* fix: Text cursor barely visible in calendar event name field (#26563)

* fix: cursor visibility in input fields

* fix: cursor visibility in input fields with suffix addons

* fix: text cursor visibility in input fields

---------

Co-authored-by: Keith Williams <keithwillcode@gmail.com>

* fix: PayPal setup page inconsistent spacing and button styling (#26612)

* chore: api v2 generate swagger only in dev (#26617)

* feat: add BUILD_FROM_BRANCH option to release-docker workflow (#26615)

* feat: add BUILD_FROM_BRANCH option to release-docker workflow

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* fix: sanitize branch names with slashes for valid Docker tags

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* refactor: extract common logic into prepare job to avoid duplication

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add Cubic AI to Devin review integration workflow (#26618)

* feat: add Cubic AI to Devin review integration workflow

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* fix: update permissions to allow posting PR comments

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* fix: remove sensitive API response logging from CI workflow

Address Cubic AI review feedback: Remove the debug log that outputs the
full Devin API response, which could expose sensitive session tokens or
authentication data in CI logs. The session URL is still logged when
successfully extracted.

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: enable/disable slots workers via env (#26621)

* chore: enable/disable slots workers via env

* fix: address Cubic AI review feedback

- Fix incorrect JSDoc comment for getSerializableContext method
- Remove debug console.log statement from slots controller
- Fix port suffix condition to preserve original behavior

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: USE_POOL env var for api v2 prisma pooling

* fix list numbering in Manual setup section of README (#26620)

* Revert "chore: USE_POOL env var for api v2 prisma pooling"

This reverts commit a970926.

* feat: limit badges to 2 with hover/click popover in UserListTable (#26556)

* feat: limit badges to 2 with hover tooltip in UserListTable

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: reuse LimitedBadges component with clickable popover for mobile

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: move LimitedBadges to components/ui with hover+click support

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: fix Biome lint issues in LimitedBadges and UserListTable

- Refactor LimitedBadges to concrete component with BadgeItem type
- Move exports to end of files to comply with useExportsLast rule
- Add explicit types to callback parameters for useExplicitType rule
- Convert nested ternary to if-else for filterType calculation
- Remove unused imports (Row, Table types)
- Update ResponseValueCell and UserListTable to use new LimitedBadges API

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* fix: add proper types for filterType and getFacetedUniqueValues

- Add FilterType import from @calcom/types/data-table
- Add FacetedValue import from @calcom/features/data-table
- Type filterType as FilterType to allow reassignment to different ColumnFilterType values
- Type getFacetedUniqueValues return as Map<FacetedValue, number>

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* add vertical gap

* fix: address code review feedback for LimitedBadges

- Add index to id for unique keys in ResponseValueCell.tsx
- Restore orange variant for group options in UserListTable.tsx
- Fix useMemo dependency array (add t, remove dispatch)
- Fix import ordering with biome
- Convert ternary operators to if-else statements for biome compliance

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: remove id from BadgeItem type, use label as key

- Remove id field from BadgeItem type in LimitedBadges
- Use label as React key instead of id
- Remove unused rowId parameter from ResponseValueCell
- Update all consumers to not pass id field

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: use index for key instead of label in LimitedBadges

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* Revert "refactor: use index for key instead of label in LimitedBadges"

This reverts commit 1daaac4.

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: add database-backed feature flag for sidebar tips section (#26516)

* chore: remove tips section from sidebar

Co-Authored-By: amit@cal.com <samit91848@gmail.com>

* chore: add feature flag for sidebar tips section

Co-Authored-By: amit@cal.com <samit91848@gmail.com>

* chore: use database-backed feature flag for sidebar tips section

Co-Authored-By: amit@cal.com <samit91848@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add automated stale PR completion workflow with Devin API (#26627)

* feat: add stale PR completion workflow with Devin API

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* feat: only trigger for community PRs (non-calcom org members)

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* refactor: use author_association pattern from pr.yml for community check

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* refactor: simplify workflow - use community label check and let Devin gather PR details

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add Devin PR conflict resolver workflow (#26624)

* feat: add Devin PR conflict resolver workflow

Adds a GitHub Actions workflow that automatically detects PRs with merge
conflicts and spins up Devin sessions to resolve them.

How it works:
1. Triggers on push to main branch (when main updates could cause conflicts)
2. Also supports manual trigger via workflow_dispatch
3. Lists all open PRs and checks their mergeable status
4. For PRs with conflicts (mergeable=false, mergeable_state=dirty):
   - Checks if a Devin session was already created (avoids duplicates)
   - Creates a new Devin session with instructions to resolve conflicts
   - Posts a comment on the PR with the Devin session link

The workflow follows the same pattern as cubic-devin-review.yml for
consistency.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: skip draft PRs in conflict detection workflow

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: use GitHub Search API to filter draft PRs at API level

Instead of filtering draft PRs in the loop, use the GitHub Search API
with 'draft:false' filter which is more efficient as it filters at the
API level rather than fetching all PRs and filtering locally.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style: remove explanatory comments from workflow

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style: remove all unnecessary explanatory comments

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: use GraphQL for batched PR fetching and labels for tracking

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add support for resolving conflicts on fork PRs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: check response.ok before parsing Devin API response

Address Cubic AI review feedback: Add response.ok check before parsing
the response body to explicitly handle HTTP error status codes from the
Devin API. This distinguishes API failures (authentication errors,
server errors) from successful responses that might be missing expected
fields.

Co-Authored-By: unknown <>

* fix: improve Devin API error logging with PR number

Co-Authored-By: unknown <>

* feat: add pr_number input for manual fork PR conflict resolution

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add maximum 15 PRs safety net limit

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: make stale PR workflow fork-aware with workflow_dispatch support (#26633)

* feat: make stale PR workflow fork-aware with workflow_dispatch support

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: add null check for pr.head.repo in stale PR workflow

When a fork is deleted after a PR is created, pr.head.repo can be null
(documented GitHub API behavior). This would cause a TypeError when
accessing properties like fork, full_name, or clone_url.

Added a null check that fails gracefully with a clear error message
when the source repository has been deleted.

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: reuse existing Devin session for Cubic AI review feedback (#26632)

* feat: reuse existing Devin session for Cubic AI review feedback

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: parse session ID from PR comments instead of API search

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: add error handling for message send API call in Cubic-Devin workflow

Addresses Cubic AI review feedback: The POST request to send a message
to an existing Devin session now checks the HTTP status code and fails
the step if the message wasn't delivered successfully. This prevents
posting a misleading comment claiming feedback was sent when the API
call actually failed.

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: Remove stale label when work is completed (#26638)

* chore: Remove stale label when work is completed

* Mark as ready for review too

* feat: add retry mechanism for UNKNOWN mergeable status PRs (#26635)

* feat: add retry mechanism for UNKNOWN mergeable status PRs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: remove redundant filtering logic for unknown mergeable status PRs

Address Cubic AI review feedback by:
- Having processPR return isTargetPR in the unknown case (like the conflict case)
- Simplifying the main loop to just push PRs to unknownPRs without re-checking
  draft status and devin label (already checked in processPR)

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: Add sentry http integration (#26634)

* chore: ignore fork PRs in devin-conflict-resolver workflow (#26640)

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* limits and advanced tabs

* availability tab

* basics tab

* black toggles!!

* new recurring, others tab and update basics

* version 1

---------

Co-authored-by: Anik Dhabal Babu <81948346+anikdhabal@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Keith Williams <keithwillcode@gmail.com>
Co-authored-by: Anshumancanrock <109489361+Anshumancanrock@users.noreply.github.com>
Co-authored-by: Morgan <33722304+ThyMinimalDev@users.noreply.github.com>
Co-authored-by: cal.com <morgan@cal.com>
Co-authored-by: Anas Najam <129951478+anzz14@users.noreply.github.com>
Co-authored-by: Eunjae Lee <hey@eunjae.dev>
Co-authored-by: Amit Sharma <74371312+Amit91848@users.noreply.github.com>
Co-authored-by: Volnei Munhoz <volnei@cal.com>
dhairyashiil added a commit that referenced this pull request Jan 10, 2026
* feat: companion alert system for browser extension

* feat: implement cross-platform alert system for browser extension

- Add ToastContext.tsx with global toast provider for managing toast state
- Add GlobalToast.tsx centered toast component for web/browser extension
- Modify alerts.ts to be platform-aware (native Alert on iOS/Android, toast on web)
- Add showInfoAlert function for informational alerts
- Update _layout.tsx to wrap app with ToastProvider and GlobalToast
- Export new toast context and alert functions from index files

* style: update toast to white/black design system

- Use white background with gray border
- Use black icons and text colors
- Match companion app design system

* open the toast at the center

* refactor: migrate event-types/index.tsx to unified alert system

- Remove inline toast state (showToast, toastMessage) and showToastMessage function
- Remove inline toast UI component at the end of the file
- Migrate all platform-specific Alert.alert calls to showSuccessAlert/showErrorAlert
- Simplifies code by using cross-platform alert utilities

* refactor: migrate useBookingActions.ts to unified alert system

- Add showSuccessAlert import alongside showErrorAlert
- Migrate all Alert.alert('Success', ...) calls to showSuccessAlert
- Affected handlers: handleSubmitReschedule, handleRescheduleWithValues,
  handleSubmitCancel, handleCancelBooking, handleConfirmBooking,
  handleRejectBooking, handleSubmitReject, handleInlineConfirm

* refactor: migrate useBookingActionModals.ts to unified alert system

- Add showSuccessAlert import alongside showErrorAlert
- Migrate all Alert.alert('Success', ...) calls to showSuccessAlert
- Affected handlers: handleAddGuests, handleUpdateLocation, handleMarkNoShow

* refactor: migrate medium-priority screens to unified alert system

- AvailabilityDetailScreen.ios.tsx: 4 Alert.alert calls migrated
- RescheduleScreen.tsx/ios/android: 3 Alert.alert calls each migrated
- EditLocationScreen.tsx/ios: 4 Alert.alert calls each migrated
- Removed unused Alert imports

* refactor: migrate remaining medium-priority screens to unified alert system

- BookingDetailScreen.tsx: 2 Alert.alert calls migrated
- AvailabilityListScreen.tsx: 1 Alert.alert call migrated
- AddGuestsScreen.tsx: 6 Alert.alert calls migrated
- MarkNoShowScreen.tsx: 2 Alert.alert calls migrated
- EditAvailabilityOverrideScreen.tsx: 4 Alert.alert calls migrated
- EditAvailabilityOverrideScreen.ios.tsx: 2 Alert.alert calls migrated
- Removed unused Alert imports

* refactor: migrate medium-priority app routes to unified alert system

Migrated 24 app route files from direct Alert.alert() calls to unified
alert utilities (showErrorAlert, showSuccessAlert, showInfoAlert):

- reschedule.tsx, reschedule.ios.tsx
- edit-location.tsx, edit-location.ios.tsx
- add-guests.tsx, add-guests.ios.tsx
- mark-no-show.tsx, mark-no-show.ios.tsx
- view-recordings.tsx, view-recordings.ios.tsx
- meeting-session-details.tsx, meeting-session-details.ios.tsx
- profile-sheet.tsx, profile-sheet.ios.tsx
- edit-availability-hours.tsx, edit-availability-hours.ios.tsx
- edit-availability-day.tsx, edit-availability-day.ios.tsx
- edit-availability-name.tsx, edit-availability-name.ios.tsx
- edit-availability-override.tsx, edit-availability-override.ios.tsx
- booking-detail.tsx, booking-detail.ios.tsx

This enables cross-platform alert support where native Alert.alert()
is used on iOS/Android and toast notifications on web (browser extension).

* refactor: migrate lower-priority components to unified alert system

Migrated Alert.alert calls to showSuccessAlert/showErrorAlert/showInfoAlert in:
- event-types/index.ios.tsx (copy link, delete, duplicate success alerts)
- event-type-detail.tsx (copy link, create/update success, validation errors, info alerts)
- deep-links.ts (error alerts for link failures)
- LogoutButton.tsx (error alert)
- BookingModals.tsx and .ios.tsx (report booking info alerts)
- AdvancedTab.tsx (info alert for unsaved event type)
- BookingListScreen.tsx (success/error/info alerts for bulk actions)

Confirmation dialogs with buttons remain as Alert.alert (out of scope).

* fix: restore Alert import for confirmation dialogs, migrate remaining info alert

- AdvancedTab.tsx: Added back Alert import for timezone selector confirmation dialog (out of scope), migrated private links info alert to showInfoAlert
- deep-links.ts: Added back Alert import for request reschedule confirmation dialog (out of scope)

* some ui dialoes were missing

* fixed multi hours ui issues on Availability detail page for android and web

* fix: add __DEV__ check for web platform in showErrorAlert

The showErrorAlert function was showing error toasts to production users
on web platform, bypassing the __DEV__ check that exists for native platforms.
This fix ensures consistent behavior across all platforms - error alerts
are only shown in development mode, while production errors are logged
to console.

Co-Authored-By: unknown <>

* fix: address dual dialogs on web and onSuccess timing issues

- BookingDetailScreen.tsx: Add Platform.OS === 'android' guard to AlertDialog
  to prevent dual dialogs rendering on web (FullScreenModal + AlertDialog)
- RescheduleScreen.android.tsx: Restore original Alert.alert with callback
  to ensure onSuccess() is called after user dismisses the alert

Co-Authored-By: unknown <>

* fix: restore Alert.alert with callback for native platforms

- AddGuestsScreen.tsx: Use platform-specific handling - Alert.alert with
  callback on iOS/Android, showSuccessAlert on web
- EditAvailabilityOverrideScreen.tsx: Same pattern - wait for user
  acknowledgment on native platforms before calling onSuccess()

Co-Authored-By: unknown <>

* fix: RescheduleScreen timing and GlobalToast useState pattern

- RescheduleScreen.tsx: Use platform-specific handling - Alert.alert with
  callback on iOS/Android, showSuccessAlert on web
- GlobalToast.tsx: Replace useMemo with useState for Animated.Value to
  guarantee instance preservation across renders

Co-Authored-By: unknown <>

* fix: restore Alert.alert with callback for iOS delete success

AvailabilityDetailScreen.ios.tsx: Use Alert.alert with callback to ensure
router.back() is called after user dismisses the success alert

Co-Authored-By: unknown <>

* feat(companion): new event type detail page  (#26678)

* fix: skip stale run-ci label check on workflow re-runs (#26590)

* fix: trust community PRs when maintainer pushes to the branch

When a maintainer merges main into a community PR branch, the new SHA
invalidates the run-ci label timing check because the label was added
before the new push. This fix adds a check to trust the PR if the
person who pushed the latest commit has write access.

This handles the case where a maintainer:
- Merges main into a community PR to resolve conflicts
- Pushes any changes to help the contributor

The security model is maintained because:
- Only users with write access can trigger this trust
- The maintainer has reviewed the code by pushing to it

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* fix: skip stale label check on workflow re-runs

Instead of implicitly trusting maintainer pushes (which could be just
a sync action without code review), use github.run_attempt to detect
re-runs. If run_attempt > 1, it means the workflow was explicitly
re-triggered (via run-ci.yml or manual re-run), so we skip the stale
label check.

This avoids the need to remove and re-add the 'run-ci' label after
syncing a community PR with main, while keeping the explicit approval
flow intact.

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* Simplify comment about re-runs in PR workflow

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Keith Williams <keithwillcode@gmail.com>

* fix: Text cursor barely visible in calendar event name field (#26563)

* fix: cursor visibility in input fields

* fix: cursor visibility in input fields with suffix addons

* fix: text cursor visibility in input fields

---------

Co-authored-by: Keith Williams <keithwillcode@gmail.com>

* fix: PayPal setup page inconsistent spacing and button styling (#26612)

* chore: api v2 generate swagger only in dev (#26617)

* feat: add BUILD_FROM_BRANCH option to release-docker workflow (#26615)

* feat: add BUILD_FROM_BRANCH option to release-docker workflow

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* fix: sanitize branch names with slashes for valid Docker tags

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* refactor: extract common logic into prepare job to avoid duplication

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add Cubic AI to Devin review integration workflow (#26618)

* feat: add Cubic AI to Devin review integration workflow

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* fix: update permissions to allow posting PR comments

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* fix: remove sensitive API response logging from CI workflow

Address Cubic AI review feedback: Remove the debug log that outputs the
full Devin API response, which could expose sensitive session tokens or
authentication data in CI logs. The session URL is still logged when
successfully extracted.

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: enable/disable slots workers via env (#26621)

* chore: enable/disable slots workers via env

* fix: address Cubic AI review feedback

- Fix incorrect JSDoc comment for getSerializableContext method
- Remove debug console.log statement from slots controller
- Fix port suffix condition to preserve original behavior

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: USE_POOL env var for api v2 prisma pooling

* fix list numbering in Manual setup section of README (#26620)

* Revert "chore: USE_POOL env var for api v2 prisma pooling"

This reverts commit a970926.

* feat: limit badges to 2 with hover/click popover in UserListTable (#26556)

* feat: limit badges to 2 with hover tooltip in UserListTable

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: reuse LimitedBadges component with clickable popover for mobile

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: move LimitedBadges to components/ui with hover+click support

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: fix Biome lint issues in LimitedBadges and UserListTable

- Refactor LimitedBadges to concrete component with BadgeItem type
- Move exports to end of files to comply with useExportsLast rule
- Add explicit types to callback parameters for useExplicitType rule
- Convert nested ternary to if-else for filterType calculation
- Remove unused imports (Row, Table types)
- Update ResponseValueCell and UserListTable to use new LimitedBadges API

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* fix: add proper types for filterType and getFacetedUniqueValues

- Add FilterType import from @calcom/types/data-table
- Add FacetedValue import from @calcom/features/data-table
- Type filterType as FilterType to allow reassignment to different ColumnFilterType values
- Type getFacetedUniqueValues return as Map<FacetedValue, number>

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* add vertical gap

* fix: address code review feedback for LimitedBadges

- Add index to id for unique keys in ResponseValueCell.tsx
- Restore orange variant for group options in UserListTable.tsx
- Fix useMemo dependency array (add t, remove dispatch)
- Fix import ordering with biome
- Convert ternary operators to if-else statements for biome compliance

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: remove id from BadgeItem type, use label as key

- Remove id field from BadgeItem type in LimitedBadges
- Use label as React key instead of id
- Remove unused rowId parameter from ResponseValueCell
- Update all consumers to not pass id field

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: use index for key instead of label in LimitedBadges

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* Revert "refactor: use index for key instead of label in LimitedBadges"

This reverts commit 1daaac4.

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: add database-backed feature flag for sidebar tips section (#26516)

* chore: remove tips section from sidebar

Co-Authored-By: amit@cal.com <samit91848@gmail.com>

* chore: add feature flag for sidebar tips section

Co-Authored-By: amit@cal.com <samit91848@gmail.com>

* chore: use database-backed feature flag for sidebar tips section

Co-Authored-By: amit@cal.com <samit91848@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add automated stale PR completion workflow with Devin API (#26627)

* feat: add stale PR completion workflow with Devin API

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* feat: only trigger for community PRs (non-calcom org members)

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* refactor: use author_association pattern from pr.yml for community check

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* refactor: simplify workflow - use community label check and let Devin gather PR details

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add Devin PR conflict resolver workflow (#26624)

* feat: add Devin PR conflict resolver workflow

Adds a GitHub Actions workflow that automatically detects PRs with merge
conflicts and spins up Devin sessions to resolve them.

How it works:
1. Triggers on push to main branch (when main updates could cause conflicts)
2. Also supports manual trigger via workflow_dispatch
3. Lists all open PRs and checks their mergeable status
4. For PRs with conflicts (mergeable=false, mergeable_state=dirty):
   - Checks if a Devin session was already created (avoids duplicates)
   - Creates a new Devin session with instructions to resolve conflicts
   - Posts a comment on the PR with the Devin session link

The workflow follows the same pattern as cubic-devin-review.yml for
consistency.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: skip draft PRs in conflict detection workflow

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: use GitHub Search API to filter draft PRs at API level

Instead of filtering draft PRs in the loop, use the GitHub Search API
with 'draft:false' filter which is more efficient as it filters at the
API level rather than fetching all PRs and filtering locally.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style: remove explanatory comments from workflow

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style: remove all unnecessary explanatory comments

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: use GraphQL for batched PR fetching and labels for tracking

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add support for resolving conflicts on fork PRs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: check response.ok before parsing Devin API response

Address Cubic AI review feedback: Add response.ok check before parsing
the response body to explicitly handle HTTP error status codes from the
Devin API. This distinguishes API failures (authentication errors,
server errors) from successful responses that might be missing expected
fields.

Co-Authored-By: unknown <>

* fix: improve Devin API error logging with PR number

Co-Authored-By: unknown <>

* feat: add pr_number input for manual fork PR conflict resolution

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add maximum 15 PRs safety net limit

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: make stale PR workflow fork-aware with workflow_dispatch support (#26633)

* feat: make stale PR workflow fork-aware with workflow_dispatch support

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: add null check for pr.head.repo in stale PR workflow

When a fork is deleted after a PR is created, pr.head.repo can be null
(documented GitHub API behavior). This would cause a TypeError when
accessing properties like fork, full_name, or clone_url.

Added a null check that fails gracefully with a clear error message
when the source repository has been deleted.

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: reuse existing Devin session for Cubic AI review feedback (#26632)

* feat: reuse existing Devin session for Cubic AI review feedback

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: parse session ID from PR comments instead of API search

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: add error handling for message send API call in Cubic-Devin workflow

Addresses Cubic AI review feedback: The POST request to send a message
to an existing Devin session now checks the HTTP status code and fails
the step if the message wasn't delivered successfully. This prevents
posting a misleading comment claiming feedback was sent when the API
call actually failed.

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: Remove stale label when work is completed (#26638)

* chore: Remove stale label when work is completed

* Mark as ready for review too

* feat: add retry mechanism for UNKNOWN mergeable status PRs (#26635)

* feat: add retry mechanism for UNKNOWN mergeable status PRs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: remove redundant filtering logic for unknown mergeable status PRs

Address Cubic AI review feedback by:
- Having processPR return isTargetPR in the unknown case (like the conflict case)
- Simplifying the main loop to just push PRs to unknownPRs without re-checking
  draft status and devin label (already checked in processPR)

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: Add sentry http integration (#26634)

* chore: ignore fork PRs in devin-conflict-resolver workflow (#26640)

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* limits and advanced tabs

* availability tab

* basics tab

* black toggles!!

* new recurring, others tab and update basics

* version 1

---------

Co-authored-by: Anik Dhabal Babu <81948346+anikdhabal@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Keith Williams <keithwillcode@gmail.com>
Co-authored-by: Anshumancanrock <109489361+Anshumancanrock@users.noreply.github.com>
Co-authored-by: Morgan <33722304+ThyMinimalDev@users.noreply.github.com>
Co-authored-by: cal.com <morgan@cal.com>
Co-authored-by: Anas Najam <129951478+anzz14@users.noreply.github.com>
Co-authored-by: Eunjae Lee <hey@eunjae.dev>
Co-authored-by: Amit Sharma <74371312+Amit91848@users.noreply.github.com>
Co-authored-by: Volnei Munhoz <volnei@cal.com>

* fix: address Cubic AI review feedback

- Add HTTP error handling for Devin API session creation in cubic-devin-review.yml
- Localize aria-label in LimitedBadges.tsx using t() function
- Improve Docker tag sanitization in release-docker.yaml to handle all invalid characters
- Avoid logging raw error objects and sensitive API response data in devin-conflict-resolver.yml
- Fix selectedSchedule dependency array issue in event-type-detail.tsx using ref pattern

Co-Authored-By: unknown <>

* chore: add translation key for show_x_more_items aria-label

Co-Authored-By: unknown <>

* fix: reset schedule ref on id change and add i18n pluralization

- Reset hasAutoSelectedScheduleRef when event type id changes to handle component reuse
- Add proper i18next pluralization variants (_one/_other) for show_x_more_items

Co-Authored-By: unknown <>

* revert: remove i18n changes from LimitedBadges and common.json

Per user request - i18n not needed in companion for now

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Anik Dhabal Babu <81948346+anikdhabal@users.noreply.github.com>
Co-authored-by: Keith Williams <keithwillcode@gmail.com>
Co-authored-by: Anshumancanrock <109489361+Anshumancanrock@users.noreply.github.com>
Co-authored-by: Morgan <33722304+ThyMinimalDev@users.noreply.github.com>
Co-authored-by: cal.com <morgan@cal.com>
Co-authored-by: Anas Najam <129951478+anzz14@users.noreply.github.com>
Co-authored-by: Eunjae Lee <hey@eunjae.dev>
Co-authored-by: Amit Sharma <74371312+Amit91848@users.noreply.github.com>
Co-authored-by: Volnei Munhoz <volnei@cal.com>
Anshumancanrock pushed a commit to Anshumancanrock/cal.com that referenced this pull request Jan 12, 2026
* feat: add Devin PR conflict resolver workflow

Adds a GitHub Actions workflow that automatically detects PRs with merge
conflicts and spins up Devin sessions to resolve them.

How it works:
1. Triggers on push to main branch (when main updates could cause conflicts)
2. Also supports manual trigger via workflow_dispatch
3. Lists all open PRs and checks their mergeable status
4. For PRs with conflicts (mergeable=false, mergeable_state=dirty):
   - Checks if a Devin session was already created (avoids duplicates)
   - Creates a new Devin session with instructions to resolve conflicts
   - Posts a comment on the PR with the Devin session link

The workflow follows the same pattern as cubic-devin-review.yml for
consistency.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: skip draft PRs in conflict detection workflow

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: use GitHub Search API to filter draft PRs at API level

Instead of filtering draft PRs in the loop, use the GitHub Search API
with 'draft:false' filter which is more efficient as it filters at the
API level rather than fetching all PRs and filtering locally.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style: remove explanatory comments from workflow

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style: remove all unnecessary explanatory comments

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: use GraphQL for batched PR fetching and labels for tracking

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add support for resolving conflicts on fork PRs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: check response.ok before parsing Devin API response

Address Cubic AI review feedback: Add response.ok check before parsing
the response body to explicitly handle HTTP error status codes from the
Devin API. This distinguishes API failures (authentication errors,
server errors) from successful responses that might be missing expected
fields.

Co-Authored-By: unknown <>

* fix: improve Devin API error logging with PR number

Co-Authored-By: unknown <>

* feat: add pr_number input for manual fork PR conflict resolution

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add maximum 15 PRs safety net limit

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Anshumancanrock added a commit to Anshumancanrock/cal.com that referenced this pull request Jan 12, 2026
* feat: companion alert system for browser extension

* feat: implement cross-platform alert system for browser extension

- Add ToastContext.tsx with global toast provider for managing toast state
- Add GlobalToast.tsx centered toast component for web/browser extension
- Modify alerts.ts to be platform-aware (native Alert on iOS/Android, toast on web)
- Add showInfoAlert function for informational alerts
- Update _layout.tsx to wrap app with ToastProvider and GlobalToast
- Export new toast context and alert functions from index files

* style: update toast to white/black design system

- Use white background with gray border
- Use black icons and text colors
- Match companion app design system

* open the toast at the center

* refactor: migrate event-types/index.tsx to unified alert system

- Remove inline toast state (showToast, toastMessage) and showToastMessage function
- Remove inline toast UI component at the end of the file
- Migrate all platform-specific Alert.alert calls to showSuccessAlert/showErrorAlert
- Simplifies code by using cross-platform alert utilities

* refactor: migrate useBookingActions.ts to unified alert system

- Add showSuccessAlert import alongside showErrorAlert
- Migrate all Alert.alert('Success', ...) calls to showSuccessAlert
- Affected handlers: handleSubmitReschedule, handleRescheduleWithValues,
  handleSubmitCancel, handleCancelBooking, handleConfirmBooking,
  handleRejectBooking, handleSubmitReject, handleInlineConfirm

* refactor: migrate useBookingActionModals.ts to unified alert system

- Add showSuccessAlert import alongside showErrorAlert
- Migrate all Alert.alert('Success', ...) calls to showSuccessAlert
- Affected handlers: handleAddGuests, handleUpdateLocation, handleMarkNoShow

* refactor: migrate medium-priority screens to unified alert system

- AvailabilityDetailScreen.ios.tsx: 4 Alert.alert calls migrated
- RescheduleScreen.tsx/ios/android: 3 Alert.alert calls each migrated
- EditLocationScreen.tsx/ios: 4 Alert.alert calls each migrated
- Removed unused Alert imports

* refactor: migrate remaining medium-priority screens to unified alert system

- BookingDetailScreen.tsx: 2 Alert.alert calls migrated
- AvailabilityListScreen.tsx: 1 Alert.alert call migrated
- AddGuestsScreen.tsx: 6 Alert.alert calls migrated
- MarkNoShowScreen.tsx: 2 Alert.alert calls migrated
- EditAvailabilityOverrideScreen.tsx: 4 Alert.alert calls migrated
- EditAvailabilityOverrideScreen.ios.tsx: 2 Alert.alert calls migrated
- Removed unused Alert imports

* refactor: migrate medium-priority app routes to unified alert system

Migrated 24 app route files from direct Alert.alert() calls to unified
alert utilities (showErrorAlert, showSuccessAlert, showInfoAlert):

- reschedule.tsx, reschedule.ios.tsx
- edit-location.tsx, edit-location.ios.tsx
- add-guests.tsx, add-guests.ios.tsx
- mark-no-show.tsx, mark-no-show.ios.tsx
- view-recordings.tsx, view-recordings.ios.tsx
- meeting-session-details.tsx, meeting-session-details.ios.tsx
- profile-sheet.tsx, profile-sheet.ios.tsx
- edit-availability-hours.tsx, edit-availability-hours.ios.tsx
- edit-availability-day.tsx, edit-availability-day.ios.tsx
- edit-availability-name.tsx, edit-availability-name.ios.tsx
- edit-availability-override.tsx, edit-availability-override.ios.tsx
- booking-detail.tsx, booking-detail.ios.tsx

This enables cross-platform alert support where native Alert.alert()
is used on iOS/Android and toast notifications on web (browser extension).

* refactor: migrate lower-priority components to unified alert system

Migrated Alert.alert calls to showSuccessAlert/showErrorAlert/showInfoAlert in:
- event-types/index.ios.tsx (copy link, delete, duplicate success alerts)
- event-type-detail.tsx (copy link, create/update success, validation errors, info alerts)
- deep-links.ts (error alerts for link failures)
- LogoutButton.tsx (error alert)
- BookingModals.tsx and .ios.tsx (report booking info alerts)
- AdvancedTab.tsx (info alert for unsaved event type)
- BookingListScreen.tsx (success/error/info alerts for bulk actions)

Confirmation dialogs with buttons remain as Alert.alert (out of scope).

* fix: restore Alert import for confirmation dialogs, migrate remaining info alert

- AdvancedTab.tsx: Added back Alert import for timezone selector confirmation dialog (out of scope), migrated private links info alert to showInfoAlert
- deep-links.ts: Added back Alert import for request reschedule confirmation dialog (out of scope)

* some ui dialoes were missing

* fixed multi hours ui issues on Availability detail page for android and web

* fix: add __DEV__ check for web platform in showErrorAlert

The showErrorAlert function was showing error toasts to production users
on web platform, bypassing the __DEV__ check that exists for native platforms.
This fix ensures consistent behavior across all platforms - error alerts
are only shown in development mode, while production errors are logged
to console.

Co-Authored-By: unknown <>

* fix: address dual dialogs on web and onSuccess timing issues

- BookingDetailScreen.tsx: Add Platform.OS === 'android' guard to AlertDialog
  to prevent dual dialogs rendering on web (FullScreenModal + AlertDialog)
- RescheduleScreen.android.tsx: Restore original Alert.alert with callback
  to ensure onSuccess() is called after user dismisses the alert

Co-Authored-By: unknown <>

* fix: restore Alert.alert with callback for native platforms

- AddGuestsScreen.tsx: Use platform-specific handling - Alert.alert with
  callback on iOS/Android, showSuccessAlert on web
- EditAvailabilityOverrideScreen.tsx: Same pattern - wait for user
  acknowledgment on native platforms before calling onSuccess()

Co-Authored-By: unknown <>

* fix: RescheduleScreen timing and GlobalToast useState pattern

- RescheduleScreen.tsx: Use platform-specific handling - Alert.alert with
  callback on iOS/Android, showSuccessAlert on web
- GlobalToast.tsx: Replace useMemo with useState for Animated.Value to
  guarantee instance preservation across renders

Co-Authored-By: unknown <>

* fix: restore Alert.alert with callback for iOS delete success

AvailabilityDetailScreen.ios.tsx: Use Alert.alert with callback to ensure
router.back() is called after user dismisses the success alert

Co-Authored-By: unknown <>

* feat(companion): new event type detail page  (calcom#26678)

* fix: skip stale run-ci label check on workflow re-runs (calcom#26590)

* fix: trust community PRs when maintainer pushes to the branch

When a maintainer merges main into a community PR branch, the new SHA
invalidates the run-ci label timing check because the label was added
before the new push. This fix adds a check to trust the PR if the
person who pushed the latest commit has write access.

This handles the case where a maintainer:
- Merges main into a community PR to resolve conflicts
- Pushes any changes to help the contributor

The security model is maintained because:
- Only users with write access can trigger this trust
- The maintainer has reviewed the code by pushing to it

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* fix: skip stale label check on workflow re-runs

Instead of implicitly trusting maintainer pushes (which could be just
a sync action without code review), use github.run_attempt to detect
re-runs. If run_attempt > 1, it means the workflow was explicitly
re-triggered (via run-ci.yml or manual re-run), so we skip the stale
label check.

This avoids the need to remove and re-add the 'run-ci' label after
syncing a community PR with main, while keeping the explicit approval
flow intact.

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* Simplify comment about re-runs in PR workflow

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Keith Williams <keithwillcode@gmail.com>

* fix: Text cursor barely visible in calendar event name field (calcom#26563)

* fix: cursor visibility in input fields

* fix: cursor visibility in input fields with suffix addons

* fix: text cursor visibility in input fields

---------

Co-authored-by: Keith Williams <keithwillcode@gmail.com>

* fix: PayPal setup page inconsistent spacing and button styling (calcom#26612)

* chore: api v2 generate swagger only in dev (calcom#26617)

* feat: add BUILD_FROM_BRANCH option to release-docker workflow (calcom#26615)

* feat: add BUILD_FROM_BRANCH option to release-docker workflow

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* fix: sanitize branch names with slashes for valid Docker tags

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* refactor: extract common logic into prepare job to avoid duplication

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add Cubic AI to Devin review integration workflow (calcom#26618)

* feat: add Cubic AI to Devin review integration workflow

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* fix: update permissions to allow posting PR comments

Co-Authored-By: keith@cal.com <keithwillcode@gmail.com>

* fix: remove sensitive API response logging from CI workflow

Address Cubic AI review feedback: Remove the debug log that outputs the
full Devin API response, which could expose sensitive session tokens or
authentication data in CI logs. The session URL is still logged when
successfully extracted.

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: enable/disable slots workers via env (calcom#26621)

* chore: enable/disable slots workers via env

* fix: address Cubic AI review feedback

- Fix incorrect JSDoc comment for getSerializableContext method
- Remove debug console.log statement from slots controller
- Fix port suffix condition to preserve original behavior

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: USE_POOL env var for api v2 prisma pooling

* fix list numbering in Manual setup section of README (calcom#26620)

* Revert "chore: USE_POOL env var for api v2 prisma pooling"

This reverts commit a970926.

* feat: limit badges to 2 with hover/click popover in UserListTable (calcom#26556)

* feat: limit badges to 2 with hover tooltip in UserListTable

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: reuse LimitedBadges component with clickable popover for mobile

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: move LimitedBadges to components/ui with hover+click support

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: fix Biome lint issues in LimitedBadges and UserListTable

- Refactor LimitedBadges to concrete component with BadgeItem type
- Move exports to end of files to comply with useExportsLast rule
- Add explicit types to callback parameters for useExplicitType rule
- Convert nested ternary to if-else for filterType calculation
- Remove unused imports (Row, Table types)
- Update ResponseValueCell and UserListTable to use new LimitedBadges API

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* fix: add proper types for filterType and getFacetedUniqueValues

- Add FilterType import from @calcom/types/data-table
- Add FacetedValue import from @calcom/features/data-table
- Type filterType as FilterType to allow reassignment to different ColumnFilterType values
- Type getFacetedUniqueValues return as Map<FacetedValue, number>

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* add vertical gap

* fix: address code review feedback for LimitedBadges

- Add index to id for unique keys in ResponseValueCell.tsx
- Restore orange variant for group options in UserListTable.tsx
- Fix useMemo dependency array (add t, remove dispatch)
- Fix import ordering with biome
- Convert ternary operators to if-else statements for biome compliance

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: remove id from BadgeItem type, use label as key

- Remove id field from BadgeItem type in LimitedBadges
- Use label as React key instead of id
- Remove unused rowId parameter from ResponseValueCell
- Update all consumers to not pass id field

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* refactor: use index for key instead of label in LimitedBadges

Co-Authored-By: eunjae@cal.com <hey@eunjae.dev>

* Revert "refactor: use index for key instead of label in LimitedBadges"

This reverts commit 1daaac4.

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: add database-backed feature flag for sidebar tips section (calcom#26516)

* chore: remove tips section from sidebar

Co-Authored-By: amit@cal.com <samit91848@gmail.com>

* chore: add feature flag for sidebar tips section

Co-Authored-By: amit@cal.com <samit91848@gmail.com>

* chore: use database-backed feature flag for sidebar tips section

Co-Authored-By: amit@cal.com <samit91848@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add automated stale PR completion workflow with Devin API (calcom#26627)

* feat: add stale PR completion workflow with Devin API

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* feat: only trigger for community PRs (non-calcom org members)

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* refactor: use author_association pattern from pr.yml for community check

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

* refactor: simplify workflow - use community label check and let Devin gather PR details

Co-Authored-By: anik@cal.com <adhabal2002@gmail.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add Devin PR conflict resolver workflow (calcom#26624)

* feat: add Devin PR conflict resolver workflow

Adds a GitHub Actions workflow that automatically detects PRs with merge
conflicts and spins up Devin sessions to resolve them.

How it works:
1. Triggers on push to main branch (when main updates could cause conflicts)
2. Also supports manual trigger via workflow_dispatch
3. Lists all open PRs and checks their mergeable status
4. For PRs with conflicts (mergeable=false, mergeable_state=dirty):
   - Checks if a Devin session was already created (avoids duplicates)
   - Creates a new Devin session with instructions to resolve conflicts
   - Posts a comment on the PR with the Devin session link

The workflow follows the same pattern as cubic-devin-review.yml for
consistency.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: skip draft PRs in conflict detection workflow

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: use GitHub Search API to filter draft PRs at API level

Instead of filtering draft PRs in the loop, use the GitHub Search API
with 'draft:false' filter which is more efficient as it filters at the
API level rather than fetching all PRs and filtering locally.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style: remove explanatory comments from workflow

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style: remove all unnecessary explanatory comments

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: use GraphQL for batched PR fetching and labels for tracking

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add support for resolving conflicts on fork PRs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: check response.ok before parsing Devin API response

Address Cubic AI review feedback: Add response.ok check before parsing
the response body to explicitly handle HTTP error status codes from the
Devin API. This distinguishes API failures (authentication errors,
server errors) from successful responses that might be missing expected
fields.

Co-Authored-By: unknown <>

* fix: improve Devin API error logging with PR number

Co-Authored-By: unknown <>

* feat: add pr_number input for manual fork PR conflict resolution

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: add maximum 15 PRs safety net limit

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: make stale PR workflow fork-aware with workflow_dispatch support (calcom#26633)

* feat: make stale PR workflow fork-aware with workflow_dispatch support

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: add null check for pr.head.repo in stale PR workflow

When a fork is deleted after a PR is created, pr.head.repo can be null
(documented GitHub API behavior). This would cause a TypeError when
accessing properties like fork, full_name, or clone_url.

Added a null check that fails gracefully with a clear error message
when the source repository has been deleted.

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat: reuse existing Devin session for Cubic AI review feedback (calcom#26632)

* feat: reuse existing Devin session for Cubic AI review feedback

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor: parse session ID from PR comments instead of API search

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: add error handling for message send API call in Cubic-Devin workflow

Addresses Cubic AI review feedback: The POST request to send a message
to an existing Devin session now checks the HTTP status code and fails
the step if the message wasn't delivered successfully. This prevents
posting a misleading comment claiming feedback was sent when the API
call actually failed.

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: Remove stale label when work is completed (calcom#26638)

* chore: Remove stale label when work is completed

* Mark as ready for review too

* feat: add retry mechanism for UNKNOWN mergeable status PRs (calcom#26635)

* feat: add retry mechanism for UNKNOWN mergeable status PRs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix: remove redundant filtering logic for unknown mergeable status PRs

Address Cubic AI review feedback by:
- Having processPR return isTargetPR in the unknown case (like the conflict case)
- Simplifying the main loop to just push PRs to unknownPRs without re-checking
  draft status and devin label (already checked in processPR)

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: Add sentry http integration (calcom#26634)

* chore: ignore fork PRs in devin-conflict-resolver workflow (calcom#26640)

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* limits and advanced tabs

* availability tab

* basics tab

* black toggles!!

* new recurring, others tab and update basics

* version 1

---------

Co-authored-by: Anik Dhabal Babu <81948346+anikdhabal@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Keith Williams <keithwillcode@gmail.com>
Co-authored-by: Anshumancanrock <109489361+Anshumancanrock@users.noreply.github.com>
Co-authored-by: Morgan <33722304+ThyMinimalDev@users.noreply.github.com>
Co-authored-by: cal.com <morgan@cal.com>
Co-authored-by: Anas Najam <129951478+anzz14@users.noreply.github.com>
Co-authored-by: Eunjae Lee <hey@eunjae.dev>
Co-authored-by: Amit Sharma <74371312+Amit91848@users.noreply.github.com>
Co-authored-by: Volnei Munhoz <volnei@cal.com>

* fix: address Cubic AI review feedback

- Add HTTP error handling for Devin API session creation in cubic-devin-review.yml
- Localize aria-label in LimitedBadges.tsx using t() function
- Improve Docker tag sanitization in release-docker.yaml to handle all invalid characters
- Avoid logging raw error objects and sensitive API response data in devin-conflict-resolver.yml
- Fix selectedSchedule dependency array issue in event-type-detail.tsx using ref pattern

Co-Authored-By: unknown <>

* chore: add translation key for show_x_more_items aria-label

Co-Authored-By: unknown <>

* fix: reset schedule ref on id change and add i18n pluralization

- Reset hasAutoSelectedScheduleRef when event type id changes to handle component reuse
- Add proper i18next pluralization variants (_one/_other) for show_x_more_items

Co-Authored-By: unknown <>

* revert: remove i18n changes from LimitedBadges and common.json

Per user request - i18n not needed in companion for now

Co-Authored-By: unknown <>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Anik Dhabal Babu <81948346+anikdhabal@users.noreply.github.com>
Co-authored-by: Keith Williams <keithwillcode@gmail.com>
Co-authored-by: Anshumancanrock <109489361+Anshumancanrock@users.noreply.github.com>
Co-authored-by: Morgan <33722304+ThyMinimalDev@users.noreply.github.com>
Co-authored-by: cal.com <morgan@cal.com>
Co-authored-by: Anas Najam <129951478+anzz14@users.noreply.github.com>
Co-authored-by: Eunjae Lee <hey@eunjae.dev>
Co-authored-by: Amit Sharma <74371312+Amit91848@users.noreply.github.com>
Co-authored-by: Volnei Munhoz <volnei@cal.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants