* fix: reuse outer tx for schedule push in commit_completed_job
Instead of calling handle_maybe_scheduled_job(db) which opens its own
connections (peak=3), inline the schedule push using a savepoint on the
outer transaction. Auth is fetched via the tx connection using
fetch_authed_from_permissioned_as_conn, and push_scheduled_job runs
on a savepoint so failures roll back only the push, not the completion.
On push failure: savepoint rolls back, schedule is disabled on the outer
tx, and the zombie return path is preserved if disabling also fails.
Peak connections drop from 3 to 1 (or 2 on cold RunnableSettings cache).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* all
* fix: extract shared try_schedule_next_job to unify schedule push paths
Replace the two diverging schedule-push implementations (inlined in
commit_completed_job and standalone handle_maybe_scheduled_job) with a
single try_schedule_next_job that reuses the caller's transaction via
savepoints. This eliminates extra pool connection usage in the
worker_flow.rs path and ensures consistent retry/error semantics.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: add failpoint markers to try_schedule_next_job
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: remove plan.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove inner retry loop from try_schedule_next_job, add caller-level retries
The 10-retry x 5s-sleep loop inside try_schedule_next_job held locks on
v2_job_completed/v2_job_queue for up to ~45s when running inside the
outer commit_completed_job transaction.
Now try_schedule_next_job makes a single attempt and returns errors to
the caller. Non-retryable errors (QuotaExceeded, NotFound) disable the
schedule immediately inside the function. Transient errors are returned
for the caller to retry:
- commit_completed_job path: outer backon retry (10x3s) retries the
entire transaction including the schedule push, so no locks are held
during sleep.
- handle_flow path: new backon retry (10x3s) wraps begin/push/commit
with a fresh transaction per attempt.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: clear push_err after successful schedule disable to prevent stuck schedules
When try_schedule_next_job disables the schedule for non-retryable errors
(NotFound, QuotaExceeded), clear the error so the caller commits the tx
(persisting the disable). Previously, the error propagated up, causing the
tx to be dropped and rolling back the disable — leaving the schedule
permanently enabled but broken.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add 5s timeout on push_scheduled_job, clean up handle_flow error handling
- Add tokio::time::timeout(5s) around push_scheduled_job inside
try_schedule_next_job to bound worst-case lock holding per attempt
- Remove unreachable QuotaExceeded/NotFound match arms in handle_flow
(these errors are handled internally by try_schedule_next_job)
- Add report_error_to_workspace_handler_or_critical_side_channel in
handle_flow when post-exhaustion schedule disable fails
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: return SchedulePushZombieError when both schedule push and disable fail
When handle_flow cannot push the next scheduled job AND cannot disable the
schedule, return a SchedulePushZombieError so the worker leaves the flow job
in the queue for zombie detection to restart. This prevents stuck schedules
where neither the next tick was pushed nor the schedule was disabled.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: prevent schedule pool connection exhaustion
Schedules were disabling themselves after upgrading from v1.605.0 to
v1.614.0 due to pool connection deadlock. The root cause was
fetch_authed_from_permissioned_as acquiring a pool connection inside
push() while a transaction already held one, exhausting the pool under
pressure.
Fix: pre-compute Authed before db.begin() for the normal path, and
reuse the transaction connection via fetch_authed_from_permissioned_as_conn
for the on_behalf_of_email path. Peak pool usage drops from 2 to 1 for
all schedule push paths.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: replace pool exhaustion tests with comprehensive schedule push tests
Replace the 16 pool-specific tests with 19 tests covering all schedule
push code paths: script/flow scheduling, on_behalf_of_email (script and
flow), retry wrapping, duplicate detection, invalid timezone/cron/args,
script/flow not found, paused schedules, clock shift detection, disabled
schedule, path mismatch, push failure disabling schedule, and trigger
metadata.
Also simplify the obo_authed pattern in push_scheduled_job to use a
single match assignment instead of two bindings with .or() chaining.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add workspace setting to disable error handler for u/ scripts/flows
Add a new workspace setting `error_handler_muted_on_user_path` that allows
disabling the error handler for jobs related to scripts/flows that start
with the "u/" prefix (user scripts/flows).
Changes:
- Add migration to add `error_handler_muted_on_user_path` column to workspace_settings
- Update WorkspaceSettings struct and get_settings query
- Update EditErrorHandler struct and edit_error_handler API endpoint
- Update error handler cache to include the new setting
- Add skip logic in send_error_to_workspace_handler for u/ paths
- Add toggle in workspace settings UI
The implementation uses the existing cached settings to avoid additional
database queries, making it efficient.
Closes#7633
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* all
* update ee private
* combine migrations
* sqlx
* fix: migration fixes for auto_invite JSONB column
- Fix TEXT[] to JSONB conversion using to_jsonb()
- Add GIN index on auto_invite for efficient ? operator queries
- Add index cleanup to down migration
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* sqlx
* all
* all
* all
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add workspace success handler with 60s TTL caching
Add a new workspace-level success handler that triggers when jobs complete
successfully, similar to the existing error handler. Key features:
- Database migration adds success_handler and success_handler_extra_args columns
- API endpoint for configuring success handler in workspace settings
- 60s TTL caching to avoid DB trips when checking handler existence
- Handler only triggers for top-level Script/Flow/SingleStepFlow jobs (not previews)
- Frontend UI with ScriptPicker and "Create from template" button for bunnative scripts
- EE warning alerts for CE users on success handler and critical alerts sections
- Backend tests for cache behavior and settings CRUD operations
The success handler receives: path, email, result, job_id, is_flow, workspace_id,
and started_at. It runs as the g/success_handler group.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: update RawCode struct in tests to use new field names
Update test to use ConcurrencySettingsWithCustom and DebouncingSettings
instead of the deprecated individual fields.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Update backend/windmill-api/src/workspaces.rs
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
* test: improve success handler test to verify job creation
Update test_success_handler_triggered_on_success to actually verify that:
- A success handler job is created in v2_job table
- The job has the correct runnable_path (configured script)
- The job runs as success_handler@windmill.dev
- The job has correct parent_job and root_job references
- The trigger starts with 'success.handler.'
This provides better test coverage for the success handler feature.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: fix success handler test and root_job parameter
- Fix test to use JobPayload::ScriptHash (JobKind::Script) instead of
JobPayload::Code (JobKind::Preview) since previews don't trigger handlers
- Add required 'lock' column to script inserts for deployed scripts
- Fix duplicate lines in workspaces.rs
- Set root_job correctly in push_success_handler
- Update test assertions to match actual behavior (root_job optimization)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* sqlx
* refactor: reduce duplication in workspace handler cache logic
- Extract database queries into fetch_error_handler_from_db and
fetch_success_handler_from_db helper functions
- Use shared WORKSPACE_HANDLER_CACHE_TTL_SECONDS constant for 60s TTL
- Reduces code from ~116 lines to ~54 lines while maintaining identical behavior
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add cache propagation warning to workspace success handler UI
Note that changes may take up to 60 seconds to propagate due to caching.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
* fix(backend): put for loop itered in a separate table
* Update SQLx metadata
---------
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* feat: show related job when deployment is in progress
- Added job_id column to deployment_metadata table to track current deployment jobs
- Updated backend to store job_id when creating dependency jobs for scripts and flows
- Modified deployment status API endpoints to include job_id in responses
- Updated frontend to display clickable job link in "Deployment in progress" badge
- Added OpenAPI schema updates for new job_id field
Resolves#7293🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* update
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
* refactor: improve usage table behavior to eliminate synchronous row locks
Replace synchronous INSERT...RETURNING with SELECT + async UPDATE pattern:
- Add check_usage_limits() to read current usage without row locks
- Add increment_usage_async() to update usage in background task
- Refactor job push logic to use optimistic validation
- Simplify job completion tracking with better error handling
This eliminates blocking row locks on the usage table during job creation,
significantly improving throughput and reducing contention.
Note: Requires running 'cargo sqlx prepare' with database access to update
the query cache in .sqlx/ directory.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Ruben Fiszel <rubenfiszel@users.noreply.github.com>
* Update SQLx metadata
* refactor: optimize cloud usage checks with caching and conditional queries
- Add 60s cache for superadmin status checks to reduce DB load
- Skip unnecessary user usage query for premium workspaces
- Use existing team plan status cache (already implemented in windmill-common)
- Update check_usage_limits to accept check_user_usage parameter
- Add sqlx query cache for conditional user usage query
This optimization eliminates redundant database queries during job creation,
particularly for premium workspaces where user usage tracking is not needed.
Co-authored-by: Ruben Fiszel <rubenfiszel@users.noreply.github.com>
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Ruben Fiszel <rubenfiszel@users.noreply.github.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
