# Automation reference and cookbook The [Automation](https://docs.weblate.org/ro/latest/admin/addons.md#addon-weblate-automation-automation) add-on runs declarative workflows using existing Weblate operations. This page describes the workflow structure, triggers, conditions, and actions. See [Cookbook](#automation-cookbook) for complete examples, including [Apply translation memory before machine translation](#automation-translation-ordering). ## Workflow definition #### Versionadded Added in version 2026.10. #### Parametrii | Nume | Required | Type or allowed values | |--------------|------------|---------------------------------------------------| | `version` | Yes | `1` | | `triggers` | Yes | List of (object); maximum items 100; unique items | | `conditions` | No | List of (condition); maximum items 100 | | `actions` | Yes | List of (action); maximum items 100 | Enter YAML or JSON in the add-on’s Workflow field. The API accepts the same structure as the `workflow` member of `configuration`. The [`JSON Schema`](https://docs.weblate.org/ro/latest/admin/_downloads/3c36c60db683d0580f9999fb3d2b94cc/automation.schema.json) describes this representation independently of the editor. Unknown keys are rejected. `version` identifies the workflow schema version, not the Weblate release. List the events to subscribe to in `triggers`, conditions that must pass before any action runs in `conditions`, and the ordered operations in `actions`. Omitting `conditions` is equivalent to an empty list. Empty `triggers` allows manual execution only; empty `actions` performs no operations. ### Literal settings and expressions Action settings are literal YAML/JSON values. Only the `value` of an `expression` condition is evaluated as CEL. Queries, engine IDs, labels, and other settings do not support CEL expressions, variable substitution, or template syntax such as `{{ unit.id }}`. A query containing that syntax is not expanded. Use [Choose](#automation-action-choose) to select actions with different fixed settings. Actions select strings using their `scope` and optional query. ### String scope Set `scope` on an action to choose its starting selection. `component` is the default and retains the existing component-wide behavior. `trigger` uses the unit affected by a change event; a source-unit change selects its corresponding target-language units. `result:ID` uses units actually changed or given new suggestions by an earlier action with that `id`. For an AI quality action, it uses units successfully evaluated by that action. Set `settings.q` to filter the selected units further. For `trigger` and `result:ID`, omitting `q` selects the whole scope. For example, a translation action with `id: machine` and `scope: trigger` can be followed by a bulk edit with `scope: result:machine`. The second action sees only units affected by the first. Source-level edits can select the corresponding target units in a later action. Workflows using `scope: trigger` can declare only change triggers. A change without a unit, or a manual run without change context, fails if execution reaches that action. A `result:ID` action fails if its referenced action did not run, for example because a branch was skipped. Preview marks result scopes as conditional because earlier actions have not run. Selections are kept only while the run is active. The activity log records affected counts and scoped unit counts (before the `q` filter), but does not store the full unit ID lists. ### Execution context CEL conditions can access the following fields. Context is captured when the run is scheduled, and only `results` changes between actions. In particular, `unit.state` is a snapshot; use `matching_strings` for current database state. Timestamps are strings, not CEL timestamp objects. #### Context fields | Domeniul | Type | Meaning | |---------------------------|--------------------------|-------------------------------------------------------------------------------------------| | `component.id` | integer | Target component ID; always present. | | `component.slug` | string | Target component slug. | | `component.project` | string | Project slug, not a project object. | | `component.category` | string or null | Category slug; null for an uncategorized component. | | `language.id` | integer | Event language ID, when language is available. | | `language.code` | string | Event language code, when language is available. | | `unit.id` | integer | Event unit ID, when unit is available. | | `unit.state` | integer | Captured string state; see [String states](#automation-string-states). | | `unit.source` | string | Source text, truncated to 4,096 characters. | | `unit.target` | string | Target text, truncated to 4,096 characters. | | `change.id` | integer | Triggering change ID, when change is available. | | `change.action` | integer | Numeric ActionEvents value, not the lowercase event name. | | `change.timestamp` | string | Change timestamp in ISO 8601 format with a timezone offset. | | `actor.id` | integer | Recorded actor ID, when actor is available. | | `actor.username` | string | Recorded actor username. | | `trigger.name` | string | Trigger identifier such as change, daily, or manual. | | `trigger.timestamp` | string | Change timestamp, or scheduling time for other triggers; ISO 8601 with a timezone offset. | | `trigger.revision` | string or null | Component local revision recorded when scheduled; null if unavailable. | | `trigger.unit_ids` | list of integers or null | Currently a one-element list when the change references a unit; otherwise null. | | `trigger.source_unit_ids` | list of integers or null | Source-unit IDs corresponding to `trigger.unit_ids`; otherwise null. | | `results` | object | Initially empty; maps action IDs to successful operation outputs. | Availability depends on the trigger: * `change` supplies `change`. It supplies `unit` and `language` only when the change references them, and `actor` from the change’s user or, if absent, its author. Any of those optional objects can be null. * `manual` supplies `actor` when initiated by a user through the UI or API. Other manual entry points may have no actor. `change`, `unit`, and `language` are null. * `daily`, `component_update`, `post_update`, `post_commit`, and `post_push` have null `actor`, `change`, `unit`, and `language`. * A preview with a change ID uses that change’s context and `trigger.name` of `change`. Without one, it uses manual context. When an object is null, its child fields cannot be accessed directly. For example, use `unit != null && unit.state == 10` or `language != null && language.code == "de"`. Prefer the typed `unit_state`, `language`, and `change_action` conditions when possible; they handle missing context and event-name conversion for you. See [Translate after source changes](#automation-event-example). ### Execution identity and permissions The usual add-on management permission authorizes configuration, preview, and manual execution. `actor` records who caused an event; it does not select the account or permissions used to perform actions. Changing a condition on `actor` only determines whether the workflow runs. Operations execute with the add-on’s authority within its configured scope, not with the triggering user’s individual translation permissions. Automatic translation receives the Automation add-on bot as its execution user and does not apply per-user operation permission checks. Reused translations can retain their original author attribution. Bulk editing calls the shared operation without a user, rather than impersonating the recorded actor. The activity context retains the actor separately from translation change attribution. Before a queued run executes, Weblate checks that the add-on is still valid and the component still belongs to its scope. The queued definition and event context are snapshots: editing the workflow after scheduling does not change that run. Operation settings are validated again against the target component at execution. ### Testing and execution Use Preview without changes to validate a workflow and inspect its conditions and planned actions. Inherited automations require a preview component ID. An optional change ID supplies event context and must belong to that component. Preview neither calls translation services nor changes strings. Conditions that depend on unexecuted action results or changed strings are marked unknown, and their branches are shown as conditional. Use Run now for real execution. The [Suplimente](https://docs.weblate.org/ro/latest/api.md#addons-api) provides equivalent preview and run operations. Runs use ordinary Celery tasks and existing operation locks. Separate runs may overlap; there are no execution modes or parallel action blocks. The activity log records the definition, context, conditions, actions, and failures. An error stops later actions without rolling back completed work. Runs are not automatically replayed; after a worker is forcibly terminated, a pending log can remain and must be inspected before manually starting another run. Changes originating from an automation, including follow-up tasks, do not start other automation runs. ### Validation and limits Workflows must contain JSON-compatible values with string mapping keys. YAML aliases, explicit tags, duplicate mapping keys, non-finite numbers, and native YAML date/timestamp values are rejected. Quote a date if a string is intended. Unknown fields are rejected, and action IDs must be unique across the entire workflow, including mutually exclusive branches. Missing required fields and wrong value types are errors; for example, `state` must be an integer, not `"10"`. Nested mappings and lists also have a structural depth limit of 32. Generated parameter tables show list limits, uniqueness requirements, numeric bounds, and string patterns from the schema. Item constraints in parentheses apply to each list element. The workflow-wide node and nesting limits below still apply even when each individual list is within its limit. Definitions are limited to 64 KiB both as submitted and as ASCII-escaped JSON after operation defaults are applied, 100 action/condition nodes, and eight nesting levels. CEL expressions are limited to 4,096 characters and evaluated in a helper process with two seconds of CPU time and five seconds of wall time per invocation. The helper also limits virtual address space to 512 MiB except on macOS, where no memory cap is enforced. The helper fails closed if a required operating-system resource limit cannot be applied. The pinned CEL runtime provides native wheels; Linux installations require a supported glibc platform. No runtime settings or separate service are required. Use [Add-on de scriere](https://docs.weblate.org/ro/latest/admin/addons.md#own-addon) for unrestricted custom Python logic on self-hosted installations. ## Declanșări Each trigger is an object in the workflow’s `triggers` list. An instance can subscribe to multiple triggers. Manual execution is always available, even when `manual` is absent from the list. ### daily #### Parametrii | Nume | Required | Type or allowed values | |-----------|------------|--------------------------| | `trigger` | Yes | `"daily"` | Runs on [Daily](https://docs.weblate.org/ro/latest/admin/addons.md#addon-event-daily), respecting [`BACKGROUND_TASKS`](https://docs.weblate.org/ro/latest/admin/config.md#std-setting-BACKGROUND_TASKS). ### component_update #### Parametrii | Nume | Required | Type or allowed values | |-----------|------------|--------------------------| | `trigger` | Yes | `"component_update"` | Runs on [Component update](https://docs.weblate.org/ro/latest/admin/addons.md#addon-event-component-update), after Weblate updates the component. ### post_update #### Parametrii | Nume | Required | Type or allowed values | |-----------|------------|--------------------------| | `trigger` | Yes | `"post_update"` | Runs on [Repository post-update](https://docs.weblate.org/ro/latest/admin/addons.md#addon-event-repository-post-update). ### post_commit #### Parametrii | Nume | Required | Type or allowed values | |-----------|------------|--------------------------| | `trigger` | Yes | `"post_commit"` | Runs on [Repository post-commit](https://docs.weblate.org/ro/latest/admin/addons.md#addon-event-repository-post-commit). ### post_push #### Parametrii | Nume | Required | Type or allowed values | |-----------|------------|--------------------------| | `trigger` | Yes | `"post_push"` | Runs on [Repository post-push](https://docs.weblate.org/ro/latest/admin/addons.md#addon-event-repository-post-push). ### manual #### Parametrii | Nume | Required | Type or allowed values | |-----------|------------|--------------------------| | `trigger` | Yes | `"manual"` | Runs when an administrator selects Run now, or requests manual execution through the [Suplimente](https://docs.weblate.org/ro/latest/api.md#addons-api). ### change #### Parametrii | Nume | Required | Type or allowed values | |-----------|------------|-----------------------------------------------------------------------------------------------------------------------------------------------| | `trigger` | Yes | `"change"` | | `events` | Yes | List of (Event name from [Selected change events](https://docs.weblate.org/ro/latest/admin/addons.md#change-actions)); minimum items 1; unique items | Subscribes to the selected [Selected change events](https://docs.weblate.org/ro/latest/admin/addons.md#change-actions). Use lowercase `ActionEvents` names with underscores, for example `source_change` or `new_source_repo`. These distinguish edits in Weblate from uploads and repository imports; `source_change` alone does not cover all three. Only changes associated with a component can start a run. ## Conditions Every condition in a list must pass. A false workflow-level condition skips the run. Conditions can also select a [Choose](#automation-action-choose) branch. Conditions concerning unavailable language, unit, or change context return false. An empty condition list passes. ### expression #### Parametrii | Nume | Required | Type or allowed values | |-------------|------------|-----------------------------| | `condition` | Yes | `"expression"` | | `value` | Yes | string; maximum length 4096 | Evaluates `value` as CEL and requires a boolean result. CEL supports arithmetic, comparisons, standard functions, and comprehensions, but cannot call Python or access the database, network, or filesystem. Expressions can use the captured execution context and outputs of earlier actions, for example `results.machine.updated > 0`. Missing fields or expression errors fail the run. ### component_category #### Parametrii | Nume | Required | Type or allowed values | |-------------|------------|-----------------------------| | `condition` | Yes | `"component_category"` | | `value` | Yes | string; maximum length 4096 | Compares the triggering component’s category slug with `value`. ### language #### Parametrii | Nume | Required | Type or allowed values | |-------------|------------|-----------------------------| | `condition` | Yes | `"language"` | | `value` | Yes | string; maximum length 4096 | Compares the event’s language code with `value`. This tests the trigger context; it does not restrict subsequent actions to that language. Use an action’s search query to restrict the strings it processes. ### matching_strings #### Parametrii | Nume | Required | Type or allowed values | |-------------|------------|-----------------------------| | `condition` | Yes | `"matching_strings"` | | `value` | Yes | string; maximum length 4096 | Passes when the component currently contains at least one string matching the [search query](https://docs.weblate.org/ro/latest/user/search.md#search-strings) in `value`. The query runs when the condition is evaluated, so it can observe changes made by earlier actions. ### change_action #### Parametrii | Nume | Required | Type or allowed values | |-------------|------------|------------------------------------------------------------------------------------------------------| | `condition` | Yes | `"change_action"` | | `value` | Yes | Event name from [Selected change events](https://docs.weblate.org/ro/latest/admin/addons.md#change-actions) | Compares the triggering change’s action with `value`. Use the lowercase event name, as for [change](#automation-trigger-change). ### unit_state #### Parametrii | Nume | Required | Type or allowed values | |-------------|------------|------------------------------------------| | `condition` | Yes | `"unit_state"` | | `value` | Yes | `0`, `10`, `11`, `12`, `20`, `30`, `100` | Compares the triggering unit’s captured state with the integer `value`. It uses the event snapshot, not a new query of the unit after earlier actions. ### and #### Parametrii | Nume | Required | Type or allowed values | |--------------|------------|----------------------------------------| | `condition` | Yes | `"and"` | | `conditions` | Yes | List of (condition); maximum items 100 | Passes when every nested condition passes. Evaluation stops at the first false condition. An empty list passes. ### or #### Parametrii | Nume | Required | Type or allowed values | |--------------|------------|----------------------------------------| | `condition` | Yes | `"or"` | | `conditions` | Yes | List of (condition); maximum items 100 | Passes when any nested condition passes. Evaluation stops at the first true condition. An empty list does not pass. ### not #### Parametrii | Nume | Required | Type or allowed values | |--------------|------------|----------------------------------------| | `condition` | Yes | `"not"` | | `conditions` | Yes | List of (condition); maximum items 100 | Negates exactly one nested condition. Empty lists and lists containing multiple conditions are invalid. ## Actions Actions run in list order. Each operation and its batched checks finish before the next action starts. Actions target the component; use [Searching for strings](https://docs.weblate.org/ro/latest/user/search.md#search-strings) queries to narrow them. Queries are evaluated when each action executes. Optional unique action IDs expose outputs as `results.`. An ID starts with a lowercase letter and contains up to 64 lowercase letters, digits, or underscores. After a successful operation, its output is stored in the activity log and, when it has an ID, in `results.` for later CEL conditions. For example, `results.memory.updated > 0` tests whether the `memory` action reported updates. Outputs belong to the current run and are not shared with other runs. Skipped, failed, and previewed operations do not create result entries. If an action might be skipped, guard access with a presence check such as `has(results.memory) && results.memory.updated > 0`. A failed operation records an error in the trace and stops later actions; its partial changes are not rolled back. Actions without IDs still record their outputs in the activity log. The YAML examples below are items to place in the workflow’s `actions` list. The cookbook provides complete workflow definitions. Settings and queries are validated against the target component before execution. For inherited workflows, labels must exist in each target project and selected engines must be enabled there. ### Traducere automată #### Versionadded Added in version 2026.10. #### Parametrii | Nume | Required | Type or allowed values | |------------------------|------------|-----------------------------------------------------------------------------| | `action` | Yes | `"weblate.automatic_translation"` | | `id` | No | string; pattern `^[a-z][a-z0-9_]{0,63}$` | | `scope` | No | `"component"`, `"trigger"`, string; pattern `^result:[a-z][a-z0-9_]{0,63}$` | | `settings` | Yes | object | | `settings.mode` | No | `"suggest"`, `"translate"`, `"fuzzy"`, `"approved"` | | `settings.q` | No | string; maximum length 4096 | | `settings.auto_source` | No | `"others"`, `"mt"` | | `settings.component` | No | integer or null; minimum 1 | | `settings.engines` | No | List of (string; maximum length 4096); maximum items 100 | | `settings.threshold` | No | integer; minimum 1; maximum 100 | #### Result fields | Nume | Required | Type or allowed values | |--------------------|------------|---------------------------------------------------------| | `component` | Yes | integer | | `updated` | Yes | integer | | `message` | Yes | string | | `warnings` | Yes | List of (string; maximum length 1024); maximum items 20 | | `warnings_omitted` | Yes | integer; minimum 0 | Runs [Traducere automată](https://docs.weblate.org/ro/latest/user/translating.md#auto-translation) synchronously. `auto_source: others` reuses translations from other components, optionally restricted by the source `component` ID. `auto_source: mt` uses the service IDs in `engines`; translation memory and AI services use the same mechanism as other providers. Defaults are `auto_source: others`, `mode: suggest`, `q: state: 0 && size(results.memory.warnings) == 0`. ### AI quality evaluation #### Versionadded Added in version 2026.10. #### Parametrii | Nume | Required | Type or allowed values | |--------------------|------------|-----------------------------------------------------------------------------| | `action` | Yes | `"weblate.ai_quality"` | | `id` | No | string; pattern `^[a-z][a-z0-9_]{0,63}$` | | `scope` | No | `"component"`, `"trigger"`, string; pattern `^result:[a-z][a-z0-9_]{0,63}$` | | `settings` | Yes | object | | `settings.service` | Yes | string; maximum length 4096 | | `settings.q` | No | string; maximum length 4096 | #### Result fields | Nume | Required | Type or allowed values | |-------------|------------|--------------------------| | `component` | Yes | integer | | `evaluated` | Yes | integer; minimum 0 | Evaluates existing target translations synchronously using the effective [AI quality evaluation add-on](https://docs.weblate.org/ro/latest/admin/addons.md#addon-weblate-ai-quality). The required `service` must match that add-on’s evaluation service and be configured for the target project. The optional `q` filters the action’s scope further; the add-on’s own query and eligibility rules still apply. Empty scoped selections make no provider requests. Each evaluated string is available to a later `result:ID` action when this action has an `id`. `evaluated` counts those strings; unit IDs are kept only during the run. The action stops later steps if a request fails, is rate limited, or its response is discarded because the string changed during evaluation. Earlier successful batches can retain their findings, so a later run may reevaluate them. See [Evaluate AI translations before approval](#automation-ai-quality-gateway) for a complete translation and review workflow. ### Bulk editing #### Versionadded Added in version 2026.10. #### Parametrii | Nume | Required | Type or allowed values | |-------------------------------------|------------|-----------------------------------------------------------------------------| | `action` | Yes | `"weblate.bulk_edit"` | | `id` | No | string; pattern `^[a-z][a-z0-9_]{0,63}$` | | `scope` | No | `"component"`, `"trigger"`, string; pattern `^result:[a-z][a-z0-9_]{0,63}$` | | `settings` | Yes | object | | `settings.q` | No | string; maximum length 4096 | | `settings.state` | No | integer | | `settings.add_flags` | No | string; maximum length 4096 | | `settings.remove_flags` | No | string; maximum length 4096 | | `settings.add_translation_flags` | No | string; maximum length 4096 | | `settings.remove_translation_flags` | No | string; maximum length 4096 | | `settings.add_labels` | No | List of (string; maximum length 4096); maximum items 100 | | `settings.remove_labels` | No | List of (string; maximum length 4096); maximum items 100 | #### Result fields | Nume | Required | Type or allowed values | |-------------|------------|--------------------------| | `component` | Yes | integer | | `updated` | Yes | integer | Uses the same operation as [Editare în masă](https://docs.weblate.org/ro/latest/admin/addons.md#addon-weblate-flags-bulk). For component scope, `q` is required and selects strings using [Searching for strings](https://docs.weblate.org/ro/latest/user/search.md#search-strings). For trigger and result scopes, `q` is optional and filters the selected strings. `state` sets an integer string state, or leaves it unchanged with -1 (the default). #### String states #### State values | Valoare | Meaning | Accepted as a bulk-edit target | |-----------|---------------------------------|----------------------------------------| | `-1` | Leave unchanged | Yes; default, not an actual unit state | | `0` | Empty | No | | `10` | Necesită editare | Yes | | `11` | Needs editing (needs rewriting) | Yes | | `12` | Needs editing (needs checking) | Yes | | `20` | Tradus | Yes | | `30` | Aprobat | Yes | | `100` | Doar în citire | No | The `unit_state` condition accepts actual unit states, including 0 and 100, but not -1. Bulk editing only changes eligible editable strings; selecting a read-only string does not make it editable. #### Flags and labels Flag settings are strings containing flags to add or remove. Label settings are lists of label names. Flag defaults are empty strings and label defaults are empty lists. Source flags and labels affect all languages, just as with the bulk-edit add-on; translation flags affect the matching translations, excluding source strings. Removing a translation flag removes its local setting; inherited flags remain in effect. Use comma-separated flags, with colon-separated parameters, for example `add_translation_flags: "max-length:100, check-glossary"`. To remove a parameterized flag, specify its name, for example `remove_translation_flags: "max-length"`. See [Personalizarea comportamentului cu ajutorul stegulețelor](https://docs.weblate.org/ro/latest/admin/checks.md#custom-checks) for quoting rules and [Controale de calitate](https://docs.weblate.org/ro/latest/user/checks.md#checks) for available checks. Labels use YAML/JSON lists of existing project label names, for example `add_labels: [needs-attention]`; this does not create a label. #### Example Mark currently translated German strings as needing editing, leaving other languages and approved strings outside the query unchanged: ```yaml - action: weblate.bulk_edit id: marked_for_edit settings: q: "language:de AND state:translated" state: 10 ``` See [Run an action only when a translation pass updates strings](#automation-conditional-actions) for a conditional bulk-edit example. #### Outputs `component` (integer) : ID of the component processed. `updated` (integer) : Count reported by the bulk-edit operation. State changes, changes to source flags or labels, and changes to translation flags contribute separately. When an action combines these operations, the same string can contribute more than once; this is not a count of distinct affected strings. Source flag and label changes are counted per source string, rather than once per language. Zero means the operation made no changes. For example, an action that only changes the states of three strings returns: ```json {"component": 42, "updated": 3} ``` A later condition can test `results.marked_for_edit.updated > 0`. This output does not contain unit IDs or a list of the changed strings. A later action must select its strings with its own query. ### Sequence #### Versionadded Added in version 2026.10. #### Parametrii | Nume | Required | Type or allowed values | |------------|------------|-------------------------------------| | `sequence` | Yes | List of (action); maximum items 100 | Groups an ordered list of actions. A sequence finishes before the next sibling action starts. It can contain operations, further sequences, and [Choose](#automation-action-choose) blocks. It does not introduce parallel execution. #### Example Group two translation passes: reuse other components first, then apply local translation memory to strings still needing translation. ```yaml - sequence: - action: weblate.automatic_translation id: reused settings: auto_source: others mode: translate q: "state: ### Choose #### Versionadded Added in version 2026.10. #### Parametrii | Nume | Required | Type or allowed values | |-----------------------|------------|----------------------------------------| | `choose` | Yes | List of (object); maximum items 100 | | `choose[].conditions` | Yes | List of (condition); maximum items 100 | | `choose[].sequence` | Yes | List of (action); maximum items 100 | | `default` | No | List of (action); maximum items 100 | Evaluates branches in order and executes the first branch whose `conditions` all pass. Each branch requires both `conditions` and `sequence`. Later branches are skipped after a match, even if the matching sequence is empty. If no branch matches, `default` runs. Omitting `default` is equivalent to an empty action list. #### Example For components in the `frontend` category, mark translated German strings as needing editing. Other components take the empty default branch. ```yaml - choose: - conditions: - condition: component_category value: frontend sequence: - action: weblate.bulk_edit id: frontend_edit settings: q: "language:de AND state:translated" state: 10 default: [] ``` See [Run an action only when a translation pass updates strings](#automation-conditional-actions) for a branch that uses an earlier action’s output instead of the component category. #### Outputs A choose block has no output object and does not accept an `id`. Only successful operations in the selected branch or default branch create result entries. Branch conditions and skipped actions are recorded in the activity trace. In this example, `results.frontend_edit` exists only if the category matches and the bulk edit succeeds. A later condition can safely check `has(results.frontend_edit) && results.frontend_edit.updated > 0`. Preview records planned or conditional actions, without creating their outputs. ## Cookbook ### Apply translation memory before machine translation Use separate automatic translation actions to give one source priority over another. This example first applies local translation memory matches scoring at least 95, then asks DeepL to translate only strings still needing translation. Enable [Memorie de traducere Weblate](https://docs.weblate.org/ro/latest/admin/machine.md#mt-weblate-translation-memory) and configure [DeepL](https://docs.weblate.org/ro/latest/admin/machine.md#mt-deepl) in the target project’s [Sugestii automate](https://docs.weblate.org/ro/latest/admin/machine.md#machine-translation-setup). Install the Automation add-on and enter this workflow: ```yaml version: 1 triggers: - trigger: component_update - trigger: daily actions: - action: weblate.automatic_translation id: memory settings: auto_source: mt engines: [weblate-translation-memory] threshold: 95 mode: translate q: "state: ### Evaluate AI translations before approval This workflow runs after repository component updates or source edits in Weblate. It applies translation memory first, translates remaining strings with OpenAI, and evaluates only strings changed by the OpenAI action. Clean strings are approved; strings with AI quality findings are marked as needing checking. Configure the translation memory and OpenAI services in the target project. Install the [AI quality evaluation](https://docs.weblate.org/ro/latest/admin/addons.md#addon-weblate-ai-quality) add-on with OpenAI as its evaluation service and its query including translated strings. Its service must match `settings.service` below. ```yaml version: 1 triggers: - trigger: component_update - trigger: change events: [source_change] actions: - action: weblate.automatic_translation id: memory settings: auto_source: mt engines: [weblate-translation-memory] threshold: 95 mode: translate q: "state: ### Run an action only when a translation pass updates strings Action IDs make outputs available to later conditions. For example, append the following item to the previous workflow’s `actions` list to mark translations from the component as needing editing when the machine translation pass updated at least one string: ```yaml - choose: - conditions: - condition: expression value: results.machine.updated > 0 sequence: - action: weblate.bulk_edit settings: q: "state:translated" state: 10 default: [] ``` The bulk-edit query selects all currently translated strings in the component, including translations that existed before the run and memory matches. It does not select only the strings updated by `machine`. Narrow the query to the intended strings before using this example. String state `10` means needing editing; it does not approve or request review of translations. `choose` executes only the first branch whose conditions pass. Here, the empty `default` performs no action when the translation pass updated no strings. During preview, the condition is unknown because `machine` has not executed. ### Translate after source changes This complete workflow listens for source edits in Weblate and new source strings from the repository. It runs only for categorized components matching either `frontend` or `backend`, and only when the change includes a nonempty unit. The action reuses other components» translations for German strings needing translation. ```yaml version: 1 triggers: - trigger: change events: [source_change, new_source_repo] conditions: - condition: and conditions: - condition: or conditions: - condition: component_category value: frontend - condition: component_category value: backend - condition: expression value: unit != null && unit.source != "" actions: - action: weblate.automatic_translation id: reused settings: auto_source: others mode: translate q: "language:de AND state: