tags. After the project summary prose, add a single subsection titled "

How can I help on this project?

" aimed at a developer. Suggest 2-3 concrete technical actions a contributor could take right now. Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, check the data for each issue: - If an issue shows a Related MR with state 'opened', do NOT suggest creating a patch or MR — one already exists. Suggest reviewing it instead. - If all Related MRs for an issue are merged, do NOT suggest reviewing them — they are already done. - If an issue is unassigned with no Related MRs, it is a good candidate to pick up. - Only suggest actions that are genuinely still needed given the current state in the data above. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Add a setup-guardrails agent skill to configure guardrails, guardrail sets, and global guardrails](https://git.drupalcode.org/project/ai/-/work_items/3586561) State: opened | Updated: 2026-07-06 | Author: Marcus Johansson (Marcus_Johansson) | Assigned: Joshua Fernandes (joshua1234511) | Labels: AI Initiative Sprint, AI Innovation, aiCoreModule, category::task Description: ## Description The AI module already ships a `create-guardrail-plugin` agent skill that *authors* new guardrail plugin classes. There is, however, no equivalent skill for *operating* the guardrails that already exist — i.e. configuring them on a running site. Site builders and agents currently have to drive the admin UI by hand to wire up guardrails, guardrail sets, and the global guardrail list. This task adds a `setup-guardrails` skill (sibling of `create-guardrail-plugin`, under `ai/.agents/skills/`) that configures guardrails rather than creating them, driven through the [Tool module](ht… ### [Add a configure-ai-settings agent skill for general AI settings (default models, providers, timeout, trusted domains)](https://git.drupalcode.org/project/ai/-/work_items/3586562) State: opened | Updated: 2026-07-06 | Author: Marcus Johansson (Marcus_Johansson) | Assigned: Joshua Fernandes (joshua1234511) | Labels: AI Initiative Sprint, AI Innovation, aiCoreModule, category::task Description: ## Description Following the same pattern as the `setup-guardrails` skill (#3586561), the AI module would benefit from a companion skill that configures the module's **general settings** on a running site, driven through the [Tool module](https://www.drupal.org/project/tool)'s tools via `drush tool:run`. Today these settings can only be inspected and changed through the admin UI at `/admin/config/ai/settings`. This task adds a `configure-ai-settings` skill (sibling of `create-guardrail-plugin` and `setup-guardrails`, under `ai/.agents/skills/`) covering the core operational settings stored i… ### [Add an AI reranking processor for Search API (owned by the AI module)](https://git.drupalcode.org/project/ai/-/work_items/3586543) State: opened | Updated: 2026-07-06 | Author: Marcus Johansson (Marcus_Johansson) | Assigned: Ahmad Khader (Ahmad-Khader) | Labels: AI Initiative Sprint, AI Product Development, aiCoreModule, category::feature Description: ### Problem/Motivation Reranking improves the precision of semantic search by re-ordering an initial result set with a dedicated rerank model (or a general-purpose LLM). AI Core already added a `rerank` operation type in [#3488114](https://www.drupal.org/project/ai/issues/3488114) (now closed), but nothing in the ecosystem consumes it yet. [#3557901 — Add Reranking Support to AI Search](https://git.drupalcode.org/project/ai_search/-/work_items/3557901) proposed adding reranking directly to AI Search. On reflection it makes more sense for the **AI module itself to own this**: reranking is a g… --- MERGE REQUESTS (24h) --- ### [3581952 add free-form metadata bag on InputInterface; seed pre/post/streaming...](https://git.drupalcode.org/project/ai/-/merge_requests/1469) State: opened | Author: Alphons Jaimon (AJV009) | Branch: 3581952-add-event-hook-1.4.x | 1335 diff lines Description: 3581952 add free-form metadata bag on InputInterface; seed pre/post/streaming events from input metadata in ProviderProxy Closes #3581952 Issue: https://git.drupalcode.org/project/ai/-/work_items/3581952 --- COMMITS (24h) --- (none) ======================================================================== ## [2] summariseModule:ai_integration_eca:developer ======================================================================== You are a technical writer producing a newsletter section about recent Drupal module activity. Module: AI Integration - ECA (machine name: ai_integration_eca) Reporting period: last 24h (2026-07-05T05:00:07+00:00 to 2026-07-06T05:00:07+00:00) You are writing for a technical developer audience. Focus on: what was merged or shipped, specific bugs fixed, APIs changed, and what is blocking progress. Be specific — mention function names, module names, and MR references where relevant. Focus your report on activity that occurred within the reporting period (comments, MRs merged, commits pushed, status changes). Use the issue description to understand what each issue is about and provide context, but do not report on the description itself as news — it is background information only. Do not list every issue/MR individually — synthesise into prose. Keep it under 200 words. Do not use emoticons or mdashes. Do not wrap usernames or contributor names in tags — mention them as plain text. When mentioning a specific issue or MR, always hyperlink it using the URL provided in the data (e.g. Issue Title or the Markdown equivalent). Do not reference issues or MRs by number alone — always use their title as the link text. Do NOT attribute any action to a named individual. Do not say who merged, fixed, reviewed, authored, or opened anything. The "Author" and "Assigned" labels in the data are context only — never surface them as "X did Y". Describe the work itself in the passive voice (e.g. "the provider refactor was merged"), not the person who did it. The author of a merge request is often not the person who completed or merged the work, so naming them is misleading. Do not name any individual people in this section. No one was active enough this period to list. Format your response as an HTML fragment. Start with
AI Integration - ECA
then use
,
,
/
, and as needed. Output only the HTML fragment with no surrounding , , or
tags. After the project summary prose, add a single subsection titled "
How can I help on this project?
" aimed at a developer. Suggest 2-3 concrete technical actions a contributor could take right now. Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, check the data for each issue: - If an issue shows a Related MR with state 'opened', do NOT suggest creating a patch or MR — one already exists. Suggest reviewing it instead. - If all Related MRs for an issue are merged, do NOT suggest reviewing them — they are already done. - If an issue is unassigned with no Related MRs, it is a good candidate to pick up. - Only suggest actions that are genuinely still needed given the current state in the data above. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Add ECA execute action for Image Classification](https://git.drupalcode.org/project/ai_integration_eca/-/work_items/3585003) State: opened | Updated: 2026-07-06 | Author: Marcus Johansson (Marcus_Johansson) | Assigned: Joonas Meriläinen (mErilainen) | Labels: AI Initiative Sprint, AI Innovation, Road to 1.0.0, category::task Description: ### Problem/Motivation The AI module's `ImageClassification` operation type has no corresponding ECA execute action in this module. ECA flows cannot drive `ImageClassification` without a custom action plugin. Existing per-operation actions: Chat, Embedding, Moderation, Speech to Text, Text to Speech (`src/Plugin/Action/`). ### Proposed resolution Add `Plugin\Action\ImageClassification` extending `AiConfigActionBase`, mirroring `Chat.php`: - Plugin id: `ai_integration_eca_execute_image_classification` - Builds the matching Input class from `Drupal\ai\OperationType\ImageClassification\` and… --- MERGE REQUESTS (24h) --- (none) --- COMMITS (24h) --- (none) ======================================================================== ## [3] summariseModule:canvas:developer ======================================================================== You are a technical writer producing a newsletter section about recent Drupal module activity. Module: Drupal Canvas (machine name: canvas) Reporting period: last 24h (2026-07-05T05:00:07+00:00 to 2026-07-06T05:00:07+00:00) You are writing for a technical developer audience. Focus on: what was merged or shipped, specific bugs fixed, APIs changed, and what is blocking progress. Be specific — mention function names, module names, and MR references where relevant. Focus your report on activity that occurred within the reporting period (comments, MRs merged, commits pushed, status changes). Use the issue description to understand what each issue is about and provide context, but do not report on the description itself as news — it is background information only. Do not list every issue/MR individually — synthesise into prose. Keep it under 200 words. Do not use emoticons or mdashes. Do not wrap usernames or contributor names in tags — mention them as plain text. When mentioning a specific issue or MR, always hyperlink it using the URL provided in the data (e.g. Issue Title or the Markdown equivalent). Do not reference issues or MRs by number alone — always use their title as the link text. Do NOT attribute any action to a named individual. Do not say who merged, fixed, reviewed, authored, or opened anything. The "Author" and "Assigned" labels in the data are context only — never surface them as "X did Y". Describe the work itself in the passive voice (e.g. "the provider refactor was merged"), not the person who did it. The author of a merge request is often not the person who completed or merged the work, so naming them is misleading. End your section with a single line listing the people who were active this period, exactly in this form (plain text, no ): "Contributors: **** (project_19391_bot_cb443e60680723bba08a5351bf595251), Gábor Hojtsy (goba), Lauri Timmanee (lauriii)". Use only the names from that list, verbatim, keeping any trailing "[N]" commit count exactly as shown. Do not introduce any other names. Format your response as an HTML fragment. Start with
Drupal Canvas
then use
,
,
/
, and as needed. Output only the HTML fragment with no surrounding , , or
tags. After the project summary prose, add a single subsection titled "
How can I help on this project?
" aimed at a developer. Suggest 2-3 concrete technical actions a contributor could take right now. Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, check the data for each issue: - If an issue shows a Related MR with state 'opened', do NOT suggest creating a patch or MR — one already exists. Suggest reviewing it instead. - If all Related MRs for an issue are merged, do NOT suggest reviewing them — they are already done. - If an issue is unassigned with no Related MRs, it is a good candidate to pick up. - Only suggest actions that are genuinely still needed given the current state in the data above. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Dependency Dashboard](https://git.drupalcode.org/project/canvas/-/work_items/3591657) State: opened | Updated: 2026-07-06 | Author: **** (project_19391_bot_cb443e60680723bba08a5351bf595251) | Assigned: unassigned | Labels: projectManagement Description: This issue lists Renovate updates and detected dependencies. Read the [Dependency Dashboard](https://docs.renovatebot.com/key-concepts/dashboard/) docs to learn more. ## Repository Problems Renovate tried to run on this repository, but found these problems. - ⚠️ WARN: Failed to set branch status - ⚠️ WARN: Rate limit exceeded for api.github.com, as no hostRules set for this host. Please set a GITHUB_COM_TOKEN - ⚠️ WARN: No tool releases found. - ⚠️ WARN: No github.com token has been configured. Skipping release notes retrieval ## Deprecations / Replacements > ⚠️ **Warning** > The foll… --- MERGE REQUESTS (24h) --- ### [fix(deps): update npm minor and patch](https://git.drupalcode.org/project/canvas/-/merge_requests/1238) State: opened | Author: **** (project_19391_bot_cb443e60680723bba08a5351bf595251) | Branch: renovate/npm-minor-and-patch | 77 diff lines Description: This MR contains the following updates: | Package | Change | [Age](https://docs.renovatebot.com/merge-confidence/) | [Confidence](https://docs.renovatebot.com/merge-confidence/) | |---|---|---|---| | [@axe-core/playwright](https://github.com/dequelabs/axe-core-npm) | [`4.11.1` → `4.12.1`](https://renovatebot.com/diffs/npm/@axe-core%2fplaywright/4.11.1/4.12.1) | ![age](https://developer.mend.io/api/mc/badges/age/npm/@axe-core%2fplaywright/4.12.1?slim=true) | ![confidence](https://developer.mend.io/api/mc/badges/confidence/npm/@axe-core%2fplaywright/4.11.1/4.12.1?slim=true) | | [@babel/parser](… ### [Draft: Stage Canvas autosaves in a dedicated Workspace](https://git.drupalcode.org/project/canvas/-/merge_requests/1056) State: opened | Author: Lauri Timmanee (lauriii) | Branch: 3588540-stage-canvas-autosaves | 4615 diff lines Description: AI-Generated: Yes, Cursor was used to assist with the creation of this MR. ## Testing instructions * [ ] Apply MR + Run update hooks * [ ] Test making changes + publishing them Closes #3588540 ### [Fix high level translation settings experience for Canvas](https://git.drupalcode.org/project/canvas/-/merge_requests/1303) State: opened | Author: Gábor Hojtsy (goba) | Branch: 3591740-fix-explanation-of-lack-of-canvas-page-language-support-to-account-for-varied-use-cases | 209 diff lines Description: [Description of changes] ## Testing instructions - [ ] First step for someone to test the changes in this MR Closes #3591740 --- COMMITS (24h) --- (none) ======================================================================== ## [4] summariseModule:ai_context:developer ======================================================================== You are a technical writer producing a newsletter section about recent Drupal module activity. Module: Context Control Center (CCC) (machine name: ai_context) Reporting period: last 24h (2026-07-05T05:00:07+00:00 to 2026-07-06T05:00:07+00:00) You are writing for a technical developer audience. Focus on: what was merged or shipped, specific bugs fixed, APIs changed, and what is blocking progress. Be specific — mention function names, module names, and MR references where relevant. Focus your report on activity that occurred within the reporting period (comments, MRs merged, commits pushed, status changes). Use the issue description to understand what each issue is about and provide context, but do not report on the description itself as news — it is background information only. Do not list every issue/MR individually — synthesise into prose. Keep it under 200 words. Do not use emoticons or mdashes. Do not wrap usernames or contributor names in tags — mention them as plain text. When mentioning a specific issue or MR, always hyperlink it using the URL provided in the data (e.g. Issue Title or the Markdown equivalent). Do not reference issues or MRs by number alone — always use their title as the link text. Do NOT attribute any action to a named individual. Do not say who merged, fixed, reviewed, authored, or opened anything. The "Author" and "Assigned" labels in the data are context only — never surface them as "X did Y". Describe the work itself in the passive voice (e.g. "the provider refactor was merged"), not the person who did it. The author of a merge request is often not the person who completed or merged the work, so naming them is misleading. End your section with a single line listing the people who were active this period, exactly in this form (plain text, no ): "Contributors: Juan Correa (jucs7), Kristen Pol (kepol)". Use only the names from that list, verbatim, keeping any trailing "[N]" commit count exactly as shown. Do not introduce any other names. Format your response as an HTML fragment. Start with
Context Control Center (CCC)
then use
,
,
/
, and as needed. Output only the HTML fragment with no surrounding , , or
tags. After the project summary prose, add a single subsection titled "
How can I help on this project?
" aimed at a developer. Suggest 2-3 concrete technical actions a contributor could take right now. Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, check the data for each issue: - If an issue shows a Related MR with state 'opened', do NOT suggest creating a patch or MR — one already exists. Suggest reviewing it instead. - If all Related MRs for an issue are merged, do NOT suggest reviewing them — they are already done. - If an issue is unassigned with no Related MRs, it is a good candidate to pick up. - Only suggest actions that are genuinely still needed given the current state in the data above. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Gather CCC contribution stats for code and non-code contributions for release notes](https://git.drupalcode.org/project/ai_context/-/work_items/3586222) State: closed | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: unassigned | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 13 Description: ## Problem/motivation The current tools for generating release notes are inadequate as they only focus on code commits. They also require the issue number to be in the commit message. I want to gather the stats for all contributors for a release including non-code contributions which there are many. ## Solution The result for release notes should be something like: ``` New Features * #12345678 (with link) * #12345678 (with link) * ... Bug Fixes * #12345678 (with link) * #12345678 (with link) * ... Other Contributions * Plan = [number] * Task = [number] * Support = [number] Contributor… ### [Reserve pre-RC1 entity schema fields for CCC](https://git.drupalcode.org/project/ai_context/-/work_items/3586161) State: closed | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: unassigned | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 10 Related MRs (already exist for this issue — check state before suggesting new contributions): - MR !133 [Issue #3586161: Add entity schema fields.](https://git.drupalcode.org/project/ai_context/-/merge_requests/133) | State: closed | Author: Kristen Pol (kepol), 371 diff lines Description: Follow up to: #3582504 _**NOTE: Before working on this issue, verify it's still relevant and makes sense.**_ **Description:** Some future features need entity fields that are easiest to reserve before stable schema settles. Adding the fields now avoids extra update hooks later while introducing little or no UI or behavior change. This issue covers schema-only reservations from the CCC context engineering recommendations, plus related pre-RC1 schema reservations referenced by the RC1 impact analysis. **Scope:** - Add `review_by` nullable datetime field to `AiContextItem`. - Add `auto_exp… ### [Create CCC beta3 release](https://git.drupalcode.org/project/ai_context/-/work_items/3586295) State: opened | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: Kristen Pol (kepol) | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 13 Description: ### Problem/Motivation Blocked by: #3586296+s Create CCC beta3 release. Tag: `1.0.0-beta3` ### Proposed resolution Create the release once at least the must-haves are done here: - #3586182+s - [beta3 milestone](https://git.drupalcode.org/project/ai_context/-/milestones/5#tab-issues) ### Target date or deadline 6 July 2026 ### Remaining tasks - Wait on must-haves - Tag code - Create the release in UI - Celebrate! ### AI usage (if applicable) - [ ] AI Assisted Issue This issue was generated with AI assistance, but was reviewed and refined by the creator. - [ ] AI Assisted Code … ### [Create a CCC release process and template](https://git.drupalcode.org/project/ai_context/-/work_items/3586321) State: opened | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: Kristen Pol (kepol) | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 13 Description: ## Problem/motivation There are a number of steps that need to happen for a release, including gathering all the contributor information (individuals and organizations) for the release notes. ## Solution Create a step-by-step process that can be turned into an issue template. It should include any tools that are used for the release notes and other steps. ### [Clean up CCC form and table accessibility cleanup](https://git.drupalcode.org/project/ai_context/-/work_items/3586304) State: opened | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: unassigned | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 13 Related MRs (already exist for this issue — check state before suggesting new contributions): - MR !205 [Issue #3586304: Clean up CCC form and table accessibility cleanup](https://git.drupalcode.org/project/ai_context/-/merge_requests/205) | State: opened | Author: Juan Correa (jucs7), 216 diff lines Description: ## Problem/motivation Follow-up to: #3586258+s Parent: #3586298+s _**Verify the issue problem and solution before proceeding.**_ **5. Form And Table Accessibility Cleanup** **Priority:** Medium **Why group these together:** These are smaller Form API and admin UI accessibility improvements. They can be handled in one cleanup issue. Includes: - `Drupal.announce()` result counts for both JS filters. - Tests for filter announcements if feasible. ## Solution ### 5.1 Replace disabled read-only selects with text **File:** - `src/Form/AiContextAgentForm.php` **Problem:** Read-only s… ### [Allow subcontext scope to override parent scope](https://git.drupalcode.org/project/ai_context/-/work_items/3586218) State: opened | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: unassigned | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 10 Description: ## Problem/motivation Follow-up to: #3576092 ## Solution From the other issue: Discussion with Emma+Aidan at UX sync: - Toggle (true/false) is defaulted to "Same as parent" (true) right above Global and then hide all of them - Description: "Disable to customize scope." Here's a [plan from cursor](https://www.drupal.org/files/issues/2026-04-21/subcontext_scope_inheritance_51216439.plan_.md) that can be updated to reflect ^ ## Tasks - [x] Add code - [x] Review code - [ ] Manually test code ## AI usage - [ ] AI assisted issue - [ ] AI assisted code - [x] AI generated code --- MERGE REQUESTS (24h) --- ### [Issue #3586251: Update subcontext feature help text and docs.](https://git.drupalcode.org/project/ai_context/-/merge_requests/169) State: merged 2026-06-20 | Author: Kristen Pol (kepol) | Branch: 3586251-issue-branch | 423 diff lines Description: Closes #3586251 --- COMMITS (24h) --- (none) ======================================================================== ## [5] summariseModule:ai_related_content:developer ======================================================================== You are a technical writer producing a newsletter section about recent Drupal module activity. Module: AI Related Content (machine name: ai_related_content) Reporting period: last 24h (2026-07-05T05:00:07+00:00 to 2026-07-06T05:00:07+00:00) You are writing for a technical developer audience. Focus on: what was merged or shipped, specific bugs fixed, APIs changed, and what is blocking progress. Be specific — mention function names, module names, and MR references where relevant. Focus your report on activity that occurred within the reporting period (comments, MRs merged, commits pushed, status changes). Use the issue description to understand what each issue is about and provide context, but do not report on the description itself as news — it is background information only. Do not list every issue/MR individually — synthesise into prose. Keep it under 200 words. Do not use emoticons or mdashes. Do not wrap usernames or contributor names in tags — mention them as plain text. When mentioning a specific issue or MR, always hyperlink it using the URL provided in the data (e.g. Issue Title or the Markdown equivalent). Do not reference issues or MRs by number alone — always use their title as the link text. Do NOT attribute any action to a named individual. Do not say who merged, fixed, reviewed, authored, or opened anything. The "Author" and "Assigned" labels in the data are context only — never surface them as "X did Y". Describe the work itself in the passive voice (e.g. "the provider refactor was merged"), not the person who did it. The author of a merge request is often not the person who completed or merged the work, so naming them is misleading. End your section with a single line listing the people who were active this period, exactly in this form (plain text, no ): "Contributors: Scott Euser (scotteuser) [1]". Use only the names from that list, verbatim, keeping any trailing "[N]" commit count exactly as shown. Do not introduce any other names. Format your response as an HTML fragment. Start with
AI Related Content
then use
,
,
/
, and as needed. Output only the HTML fragment with no surrounding , , or
tags. After the project summary prose, add a single subsection titled "
How can I help on this project?
" aimed at a developer. Suggest 2-3 concrete technical actions a contributor could take right now. Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, check the data for each issue: - If an issue shows a Related MR with state 'opened', do NOT suggest creating a patch or MR — one already exists. Suggest reviewing it instead. - If all Related MRs for an issue are merged, do NOT suggest reviewing them — they are already done. - If an issue is unassigned with no Related MRs, it is a good candidate to pick up. - Only suggest actions that are genuinely still needed given the current state in the data above. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Drupal 10 compatibility](https://git.drupalcode.org/project/ai_related_content/-/work_items/3576580) State: opened | Updated: 2026-07-06 | Author: Scott Euser (scotteuser) | Assigned: Scott Euser (scotteuser) | Labels: Related MRs (already exist for this issue — check state before suggesting new contributions): - MR !29 [Resolve "Drupal 10 compatibility" 2x](https://git.drupalcode.org/project/ai_related_content/-/merge_requests/29) | State: opened | Author: Scott Euser (scotteuser), 64 diff lines Description: ## Summary Need legacy hooks ### [Access checks hardening prior to stable](https://git.drupalcode.org/project/ai_related_content/-/work_items/3576579) State: closed | Updated: 2026-07-05 | Author: Scott Euser (scotteuser) | Assigned: Scott Euser (scotteuser) | Labels: Related MRs (already exist for this issue — check state before suggesting new contributions): - MR !27 [Resolve "Access checks hardening prior to stable" 2x](https://git.drupalcode.org/project/ai_related_content/-/merge_requests/27) | State: merged 2026-07-05 | Author: Scott Euser (scotteuser), 572 diff lines Description: ## Description More warnings about how to configure the Search API best --- MERGE REQUESTS (24h) --- ### [Resolve "Drupal 10 compatibility" 1x](https://git.drupalcode.org/project/ai_related_content/-/merge_requests/28) State: merged 2026-07-06 | Author: Scott Euser (scotteuser) | Branch: 3576580-drupal-10-compatibility-1x | 64 diff lines Description: Closes #3576580 ### [Resolve "Access checks hardening prior to stable" 1x](https://git.drupalcode.org/project/ai_related_content/-/merge_requests/26) State: merged 2026-07-05 | Author: Scott Euser (scotteuser) | Branch: 3576579-access-checks-hardening-1.x | 439 diff lines Description: Closes #3576579 --- COMMITS (24h) --- - [e7b57f0d](https://git.drupalcode.org/project/ai_related_content/-/commit/e7b57f0ddb157e95848343404c773525352d4e0a) fix: #3576579 Access checks hardening prior to stable — Scott Euser (2026-07-05T05:21:40.000+00:00) ======================================================================== ## [6] generateTldr:developer ======================================================================== You are an editor distilling a Drupal AI project newsletter into its most important highlights. You are writing for a technical developer audience. Be specific — name modules, merged features, and critical bugs. Read all the module summaries below. Separate the highlights into two categories: - SHIPPED: things that were merged, fixed, released, or completed during this period. - ONGOING: things that are actively in progress, under review, or blocked. Be specific — name the module, what happened, and why it matters. Do not use emoticons or mdashes. Do not include any text outside the two sections. When you mention a specific issue or merge request, add an inline citation using [N] where N is the reference number from the list below. You may cite multiple references per item, e.g. [1][3]. Place citations immediately after the relevant phrase, before any punctuation. Format as two HTML sections. Use exactly this structure (all
elements must be inside the
, never outside it):
Shipped

Title here — One sentence explanation [1].

Another title — One sentence explanation.

Ongoing

Title here — One sentence explanation [2].

Up to 5 items per section. Do not output any text, tags, or characters outside these two sections. Output only the HTML fragment, no surrounding tags. --- REFERENCE LIST --- [1] Add a setup-guardrails agent skill to configure guardrails, guardrail sets, and global guardrails (ai, Issue) — https://git.drupalcode.org/project/ai/-/work_items/3586561 [2] Add a configure-ai-settings agent skill for general AI settings (default models, providers, timeout, trusted domains) (ai, Issue) — https://git.drupalcode.org/project/ai/-/work_items/3586562 [3] Add an AI reranking processor for Search API (owned by the AI module) (ai, Issue) — https://git.drupalcode.org/project/ai/-/work_items/3586543 [4] 3581952 add free-form metadata bag on InputInterface; seed pre/post/streaming... (ai, MR) — https://git.drupalcode.org/project/ai/-/merge_requests/1469 [5] Add ECA execute action for Image Classification (ai_integration_eca, Issue) — https://git.drupalcode.org/project/ai_integration_eca/-/work_items/3585003 [6] Dependency Dashboard (canvas, Issue) — https://git.drupalcode.org/project/canvas/-/work_items/3591657 [7] fix(deps): update npm minor and patch (canvas, MR) — https://git.drupalcode.org/project/canvas/-/merge_requests/1238 [8] Draft: Stage Canvas autosaves in a dedicated Workspace (canvas, MR) — https://git.drupalcode.org/project/canvas/-/merge_requests/1056 [9] Fix high level translation settings experience for Canvas (canvas, MR) — https://git.drupalcode.org/project/canvas/-/merge_requests/1303 [10] Gather CCC contribution stats for code and non-code contributions for release notes (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586222 [11] Reserve pre-RC1 entity schema fields for CCC (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586161 [12] Create CCC beta3 release (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586295 [13] Create a CCC release process and template (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586321 [14] Clean up CCC form and table accessibility cleanup (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586304 [15] Allow subcontext scope to override parent scope (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586218 [16] Issue #3586161: Add entity schema fields. (ai_context, MR) — https://git.drupalcode.org/project/ai_context/-/merge_requests/133 [17] Issue #3586251: Update subcontext feature help text and docs. (ai_context, MR) — https://git.drupalcode.org/project/ai_context/-/merge_requests/169 [18] Issue #3586304: Clean up CCC form and table accessibility cleanup (ai_context, MR) — https://git.drupalcode.org/project/ai_context/-/merge_requests/205 [19] Drupal 10 compatibility (ai_related_content, Issue) — https://git.drupalcode.org/project/ai_related_content/-/work_items/3576580 [20] Access checks hardening prior to stable (ai_related_content, Issue) — https://git.drupalcode.org/project/ai_related_content/-/work_items/3576579 [21] Resolve "Drupal 10 compatibility" 2x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/29 [22] Resolve "Drupal 10 compatibility" 1x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/28 [23] Resolve "Access checks hardening prior to stable" 1x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/26 [24] Resolve "Access checks hardening prior to stable" 2x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/27 --- MODULE SUMMARIES ---
AI (Artificial Intelligence)

Development activity over the past 24 hours focused on scoping new agent skills and event infrastructure, though no merges or commits landed during this window.

Three new issues were opened and assigned to expand the module's agent skill library for site configuration. Add a setup-guardrails agent skill to configure guardrails, guardrail sets, and global guardrails and Add a configure-ai-settings agent skill for general AI settings both propose new skills under ai/.agents/skills/ that will drive configuration through the Tool module rather than requiring manual admin UI interaction. Meanwhile, Add an AI reranking processor for Search API proposes moving reranking support into the AI module itself as a Search API processor, leveraging the rerank operation type added in #3488114.

An open merge request on issue #3581952 adds a free-form metadata bag to InputInterface and seeds pre/post/streaming events from input metadata in ProviderProxy, spanning 1335 lines of diff. This work remains under review.

How can I help on this project?

Review the InputInterface metadata bag and event seeding MR to help unblock event hook infrastructure. Pick up the Search API reranking processor feature if you have experience with Search API processor plugins. Test and provide feedback on the proposed agent skill architecture.
Contributors: Alphons Jaimon (AJV009) ---
AI Integration - ECA

Activity remained quiet over the past 24 hours with no merge requests or commits pushed. The module's integration layer between the AI module and ECA (Event-Condition-Action) continues to track coverage gaps for AI operation types.

The outstanding Add ECA execute action for Image Classification issue was updated during the reporting period. This task targets the missing ECA action plugin for the ImageClassification operation type, which would follow the established pattern in existing action plugins (Chat, Embedding, Moderation, Speech to Text, Text to Speech) by extending AiConfigActionBase. The proposed implementation would expose ImageClassification capabilities to ECA flows, allowing site builders to trigger image classification operations through the ECA UI without custom code.

How can I help on this project?

Pick up the unassigned Image Classification action task and implement the Plugin\Action\ImageClassification class following the existing action plugin patterns. Review the existing Chat.php implementation as a reference for extending AiConfigActionBase and building the appropriate Input class.
---
Drupal Canvas

Activity this period focused on dependency management and ongoing feature development. A merge request to update npm minor and patch dependencies was opened, updating @axe-core/playwright from 4.11.1 to 4.12.1 among other package updates. The Dependency Dashboard continues to surface warnings about rate limits and missing GitHub tokens affecting release notes retrieval.

Two significant feature branches remain in progress. Work continues on staging Canvas autosaves in a dedicated Workspace, a large changeset spanning over 4,600 lines that introduces workspace-based autosave functionality. A new merge request was opened to fix high level translation settings experience for Canvas, addressing explanation of language support limitations across varied use cases with approximately 200 lines of changes.

How can I help on this project?

Review MR 1056 for workspace-based autosave functionality, testing the update hooks and publishing workflow. Review MR 1303 to validate translation settings improvements. Test npm dependency updates for compatibility issues.

Contributors: **** (project_19391_bot_cb443e60680723bba08a5351bf595251), Gábor Hojtsy (goba), Lauri Timmanee (lauriii)
---
Context Control Center (CCC)

Activity focused on release preparation and accessibility improvements. The Reserve pre-RC1 entity schema fields for CCC issue was closed, completing the addition of nullable datetime fields for review_by and auto_expiration to AiContextItem entities, along with status and category fields. The Gather CCC contribution stats for code and non-code contributions for release notes issue was also closed, addressing the need for comprehensive contributor tracking beyond code commits.

Planning continued for the upcoming beta3 release, with Create CCC beta3 release targeting July 6, 2026 and blocked by must-have issues. A related Create a CCC release process and template issue was opened to formalize the release workflow including contributor attribution.

Work progressed on Clean up CCC form and table accessibility cleanup with an open merge request addressing Drupal.announce() result counts for JavaScript filters and replacing disabled read-only selects with text in AiContextAgentForm.php. The Allow subcontext scope to override parent scope issue remains in manual testing phase.

How can I help on this project?

Review the open accessibility cleanup merge request which includes Drupal.announce() improvements and form modifications. Help with manual testing on the subcontext scope override functionality. Check the beta3 milestone for additional issues needing attention before the July 6 release.
Contributors: Juan Correa (jucs7), Kristen Pol (kepol) ---
AI Related Content

The AI Related Content module saw progress on compatibility and security hardening over the reporting period. The Access checks hardening prior to stable issue was closed after MR !27 and MR !26 were merged, adding warnings and guidance around Search API configuration best practices. This work totaled over 1,000 lines of changes aimed at strengthening access controls before a stable release.

Work on Drupal 10 compatibility advanced with the merge of MR !28, which addresses legacy hook requirements. However, MR !29 remains open for this issue, indicating additional compatibility work is still in progress.

How can I help on this project?

Review the open MR !29 for Drupal 10 compatibility to help move it toward merge. Test the recent access control hardening changes with various Search API configurations to validate the new warnings and guidance work as intended in real-world scenarios.

Contributors: Scott Euser (scotteuser) [1]
======================================================================== ## [7] factcheck:tldr:developer ======================================================================== Layer-1 corrections: 2 Judge flags: 3 ======================================================================== ## [8] summariseModule:ai:executive ======================================================================== You are a technical writer producing a newsletter section about recent Drupal module activity. Module: AI (Artificial Intelligence) (machine name: ai) Reporting period: last 24h (2026-07-05T05:00:07+00:00 to 2026-07-06T05:00:07+00:00) You are writing for a non-technical executive audience (CEO/leadership level). Focus on: business impact, strategic progress, risks, and what is being delivered. Avoid technical jargon. Do not mention branch names, function names, or API details. Explain what each piece of work means for users or the project's goals. Keep risk language proportionate to the stage of the software. For alpha or beta modules, unassigned bugs or open issues are normal and expected — do not describe them as 'reputational risks' or use alarmist framing. Reserve strong risk language for issues that are genuinely critical or blocking a stable release. Focus your report on activity that occurred within the reporting period (comments, MRs merged, commits pushed, status changes). Use the issue description to understand what each issue is about and provide context, but do not report on the description itself as news — it is background information only. Do not list every issue/MR individually — synthesise into prose. Keep it under 200 words. Do not use emoticons or mdashes. Do not wrap usernames or contributor names in tags — mention them as plain text. When mentioning a specific issue or MR, always hyperlink it using the URL provided in the data (e.g. Issue Title or the Markdown equivalent). Do not reference issues or MRs by number alone — always use their title as the link text. Do NOT attribute any action to a named individual. Do not say who merged, fixed, reviewed, authored, or opened anything. The "Author" and "Assigned" labels in the data are context only — never surface them as "X did Y". Describe the work itself in the passive voice (e.g. "the provider refactor was merged"), not the person who did it. The author of a merge request is often not the person who completed or merged the work, so naming them is misleading. End your section with a single line listing the people who were active this period, exactly in this form (plain text, no ): "Contributors: Alphons Jaimon (AJV009)". Use only the names from that list, verbatim, keeping any trailing "[N]" commit count exactly as shown. Do not introduce any other names. Format your response as an HTML fragment. Start with
AI (Artificial Intelligence)
then use
,
,
/
, and as needed. Output only the HTML fragment with no surrounding , , or
tags. After the project summary prose, add a single subsection titled "
How can I help on this project?
" aimed at a non-technical executive. Suggest 2-3 concrete, high-level ways a leader could support or unblock progress (e.g. resourcing, stakeholder alignment, decision-making, funding, advocacy). Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, verify it against the issue data. Do not suggest actions that are already in progress or covered by an existing MR — for example, do not suggest that work needs to be started if an issue already has a Related MR. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Add a setup-guardrails agent skill to configure guardrails, guardrail sets, and global guardrails](https://git.drupalcode.org/project/ai/-/work_items/3586561) State: opened | Updated: 2026-07-06 | Author: Marcus Johansson (Marcus_Johansson) | Assigned: Joshua Fernandes (joshua1234511) | Labels: AI Initiative Sprint, AI Innovation, aiCoreModule, category::task Description: ## Description The AI module already ships a `create-guardrail-plugin` agent skill that *authors* new guardrail plugin classes. There is, however, no equivalent skill for *operating* the guardrails that already exist — i.e. configuring them on a running site. Site builders and agents currently have to drive the admin UI by hand to wire up guardrails, guardrail sets, and the global guardrail list. This task adds a `setup-guardrails` skill (sibling of `create-guardrail-plugin`, under `ai/.agents/skills/`) that configures guardrails rather than creating them, driven through the [Tool module](ht… ### [Add a configure-ai-settings agent skill for general AI settings (default models, providers, timeout, trusted domains)](https://git.drupalcode.org/project/ai/-/work_items/3586562) State: opened | Updated: 2026-07-06 | Author: Marcus Johansson (Marcus_Johansson) | Assigned: Joshua Fernandes (joshua1234511) | Labels: AI Initiative Sprint, AI Innovation, aiCoreModule, category::task Description: ## Description Following the same pattern as the `setup-guardrails` skill (#3586561), the AI module would benefit from a companion skill that configures the module's **general settings** on a running site, driven through the [Tool module](https://www.drupal.org/project/tool)'s tools via `drush tool:run`. Today these settings can only be inspected and changed through the admin UI at `/admin/config/ai/settings`. This task adds a `configure-ai-settings` skill (sibling of `create-guardrail-plugin` and `setup-guardrails`, under `ai/.agents/skills/`) covering the core operational settings stored i… ### [Add an AI reranking processor for Search API (owned by the AI module)](https://git.drupalcode.org/project/ai/-/work_items/3586543) State: opened | Updated: 2026-07-06 | Author: Marcus Johansson (Marcus_Johansson) | Assigned: Ahmad Khader (Ahmad-Khader) | Labels: AI Initiative Sprint, AI Product Development, aiCoreModule, category::feature Description: ### Problem/Motivation Reranking improves the precision of semantic search by re-ordering an initial result set with a dedicated rerank model (or a general-purpose LLM). AI Core already added a `rerank` operation type in [#3488114](https://www.drupal.org/project/ai/issues/3488114) (now closed), but nothing in the ecosystem consumes it yet. [#3557901 — Add Reranking Support to AI Search](https://git.drupalcode.org/project/ai_search/-/work_items/3557901) proposed adding reranking directly to AI Search. On reflection it makes more sense for the **AI module itself to own this**: reranking is a g… --- MERGE REQUESTS (24h) --- ### [3581952 add free-form metadata bag on InputInterface; seed pre/post/streaming...](https://git.drupalcode.org/project/ai/-/merge_requests/1469) State: opened | Author: Alphons Jaimon (AJV009) | Branch: 3581952-add-event-hook-1.4.x | 1335 diff lines Description: 3581952 add free-form metadata bag on InputInterface; seed pre/post/streaming events from input metadata in ProviderProxy Closes #3581952 Issue: https://git.drupalcode.org/project/ai/-/work_items/3581952 --- COMMITS (24h) --- (none) ======================================================================== ## [9] summariseModule:ai_integration_eca:executive ======================================================================== You are a technical writer producing a newsletter section about recent Drupal module activity. Module: AI Integration - ECA (machine name: ai_integration_eca) Reporting period: last 24h (2026-07-05T05:00:07+00:00 to 2026-07-06T05:00:07+00:00) You are writing for a non-technical executive audience (CEO/leadership level). Focus on: business impact, strategic progress, risks, and what is being delivered. Avoid technical jargon. Do not mention branch names, function names, or API details. Explain what each piece of work means for users or the project's goals. Keep risk language proportionate to the stage of the software. For alpha or beta modules, unassigned bugs or open issues are normal and expected — do not describe them as 'reputational risks' or use alarmist framing. Reserve strong risk language for issues that are genuinely critical or blocking a stable release. Focus your report on activity that occurred within the reporting period (comments, MRs merged, commits pushed, status changes). Use the issue description to understand what each issue is about and provide context, but do not report on the description itself as news — it is background information only. Do not list every issue/MR individually — synthesise into prose. Keep it under 200 words. Do not use emoticons or mdashes. Do not wrap usernames or contributor names in tags — mention them as plain text. When mentioning a specific issue or MR, always hyperlink it using the URL provided in the data (e.g. Issue Title or the Markdown equivalent). Do not reference issues or MRs by number alone — always use their title as the link text. Do NOT attribute any action to a named individual. Do not say who merged, fixed, reviewed, authored, or opened anything. The "Author" and "Assigned" labels in the data are context only — never surface them as "X did Y". Describe the work itself in the passive voice (e.g. "the provider refactor was merged"), not the person who did it. The author of a merge request is often not the person who completed or merged the work, so naming them is misleading. Do not name any individual people in this section. No one was active enough this period to list. Format your response as an HTML fragment. Start with
AI Integration - ECA
then use
,
,
/
, and as needed. Output only the HTML fragment with no surrounding , , or
tags. After the project summary prose, add a single subsection titled "
How can I help on this project?
" aimed at a non-technical executive. Suggest 2-3 concrete, high-level ways a leader could support or unblock progress (e.g. resourcing, stakeholder alignment, decision-making, funding, advocacy). Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, verify it against the issue data. Do not suggest actions that are already in progress or covered by an existing MR — for example, do not suggest that work needs to be started if an issue already has a Related MR. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Add ECA execute action for Image Classification](https://git.drupalcode.org/project/ai_integration_eca/-/work_items/3585003) State: opened | Updated: 2026-07-06 | Author: Marcus Johansson (Marcus_Johansson) | Assigned: Joonas Meriläinen (mErilainen) | Labels: AI Initiative Sprint, AI Innovation, Road to 1.0.0, category::task Description: ### Problem/Motivation The AI module's `ImageClassification` operation type has no corresponding ECA execute action in this module. ECA flows cannot drive `ImageClassification` without a custom action plugin. Existing per-operation actions: Chat, Embedding, Moderation, Speech to Text, Text to Speech (`src/Plugin/Action/`). ### Proposed resolution Add `Plugin\Action\ImageClassification` extending `AiConfigActionBase`, mirroring `Chat.php`: - Plugin id: `ai_integration_eca_execute_image_classification` - Builds the matching Input class from `Drupal\ai\OperationType\ImageClassification\` and… --- MERGE REQUESTS (24h) --- (none) --- COMMITS (24h) --- (none) ======================================================================== ## [10] summariseModule:canvas:executive ======================================================================== You are a technical writer producing a newsletter section about recent Drupal module activity. Module: Drupal Canvas (machine name: canvas) Reporting period: last 24h (2026-07-05T05:00:07+00:00 to 2026-07-06T05:00:07+00:00) You are writing for a non-technical executive audience (CEO/leadership level). Focus on: business impact, strategic progress, risks, and what is being delivered. Avoid technical jargon. Do not mention branch names, function names, or API details. Explain what each piece of work means for users or the project's goals. Keep risk language proportionate to the stage of the software. For alpha or beta modules, unassigned bugs or open issues are normal and expected — do not describe them as 'reputational risks' or use alarmist framing. Reserve strong risk language for issues that are genuinely critical or blocking a stable release. Focus your report on activity that occurred within the reporting period (comments, MRs merged, commits pushed, status changes). Use the issue description to understand what each issue is about and provide context, but do not report on the description itself as news — it is background information only. Do not list every issue/MR individually — synthesise into prose. Keep it under 200 words. Do not use emoticons or mdashes. Do not wrap usernames or contributor names in tags — mention them as plain text. When mentioning a specific issue or MR, always hyperlink it using the URL provided in the data (e.g. Issue Title or the Markdown equivalent). Do not reference issues or MRs by number alone — always use their title as the link text. Do NOT attribute any action to a named individual. Do not say who merged, fixed, reviewed, authored, or opened anything. The "Author" and "Assigned" labels in the data are context only — never surface them as "X did Y". Describe the work itself in the passive voice (e.g. "the provider refactor was merged"), not the person who did it. The author of a merge request is often not the person who completed or merged the work, so naming them is misleading. End your section with a single line listing the people who were active this period, exactly in this form (plain text, no ): "Contributors: **** (project_19391_bot_cb443e60680723bba08a5351bf595251), Gábor Hojtsy (goba), Lauri Timmanee (lauriii)". Use only the names from that list, verbatim, keeping any trailing "[N]" commit count exactly as shown. Do not introduce any other names. Format your response as an HTML fragment. Start with
Drupal Canvas
then use
,
,
/
, and as needed. Output only the HTML fragment with no surrounding , , or
tags. After the project summary prose, add a single subsection titled "
How can I help on this project?
" aimed at a non-technical executive. Suggest 2-3 concrete, high-level ways a leader could support or unblock progress (e.g. resourcing, stakeholder alignment, decision-making, funding, advocacy). Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, verify it against the issue data. Do not suggest actions that are already in progress or covered by an existing MR — for example, do not suggest that work needs to be started if an issue already has a Related MR. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Dependency Dashboard](https://git.drupalcode.org/project/canvas/-/work_items/3591657) State: opened | Updated: 2026-07-06 | Author: **** (project_19391_bot_cb443e60680723bba08a5351bf595251) | Assigned: unassigned | Labels: projectManagement Description: This issue lists Renovate updates and detected dependencies. Read the [Dependency Dashboard](https://docs.renovatebot.com/key-concepts/dashboard/) docs to learn more. ## Repository Problems Renovate tried to run on this repository, but found these problems. - ⚠️ WARN: Failed to set branch status - ⚠️ WARN: Rate limit exceeded for api.github.com, as no hostRules set for this host. Please set a GITHUB_COM_TOKEN - ⚠️ WARN: No tool releases found. - ⚠️ WARN: No github.com token has been configured. Skipping release notes retrieval ## Deprecations / Replacements > ⚠️ **Warning** > The foll… --- MERGE REQUESTS (24h) --- ### [fix(deps): update npm minor and patch](https://git.drupalcode.org/project/canvas/-/merge_requests/1238) State: opened | Author: **** (project_19391_bot_cb443e60680723bba08a5351bf595251) | Branch: renovate/npm-minor-and-patch | 77 diff lines Description: This MR contains the following updates: | Package | Change | [Age](https://docs.renovatebot.com/merge-confidence/) | [Confidence](https://docs.renovatebot.com/merge-confidence/) | |---|---|---|---| | [@axe-core/playwright](https://github.com/dequelabs/axe-core-npm) | [`4.11.1` → `4.12.1`](https://renovatebot.com/diffs/npm/@axe-core%2fplaywright/4.11.1/4.12.1) | ![age](https://developer.mend.io/api/mc/badges/age/npm/@axe-core%2fplaywright/4.12.1?slim=true) | ![confidence](https://developer.mend.io/api/mc/badges/confidence/npm/@axe-core%2fplaywright/4.11.1/4.12.1?slim=true) | | [@babel/parser](… ### [Draft: Stage Canvas autosaves in a dedicated Workspace](https://git.drupalcode.org/project/canvas/-/merge_requests/1056) State: opened | Author: Lauri Timmanee (lauriii) | Branch: 3588540-stage-canvas-autosaves | 4615 diff lines Description: AI-Generated: Yes, Cursor was used to assist with the creation of this MR. ## Testing instructions * [ ] Apply MR + Run update hooks * [ ] Test making changes + publishing them Closes #3588540 ### [Fix high level translation settings experience for Canvas](https://git.drupalcode.org/project/canvas/-/merge_requests/1303) State: opened | Author: Gábor Hojtsy (goba) | Branch: 3591740-fix-explanation-of-lack-of-canvas-page-language-support-to-account-for-varied-use-cases | 209 diff lines Description: [Description of changes] ## Testing instructions - [ ] First step for someone to test the changes in this MR Closes #3591740 --- COMMITS (24h) --- (none) ======================================================================== ## [11] summariseModule:ai_context:executive ======================================================================== You are a technical writer producing a newsletter section about recent Drupal module activity. Module: Context Control Center (CCC) (machine name: ai_context) Reporting period: last 24h (2026-07-05T05:00:07+00:00 to 2026-07-06T05:00:07+00:00) You are writing for a non-technical executive audience (CEO/leadership level). Focus on: business impact, strategic progress, risks, and what is being delivered. Avoid technical jargon. Do not mention branch names, function names, or API details. Explain what each piece of work means for users or the project's goals. Keep risk language proportionate to the stage of the software. For alpha or beta modules, unassigned bugs or open issues are normal and expected — do not describe them as 'reputational risks' or use alarmist framing. Reserve strong risk language for issues that are genuinely critical or blocking a stable release. Focus your report on activity that occurred within the reporting period (comments, MRs merged, commits pushed, status changes). Use the issue description to understand what each issue is about and provide context, but do not report on the description itself as news — it is background information only. Do not list every issue/MR individually — synthesise into prose. Keep it under 200 words. Do not use emoticons or mdashes. Do not wrap usernames or contributor names in tags — mention them as plain text. When mentioning a specific issue or MR, always hyperlink it using the URL provided in the data (e.g. Issue Title or the Markdown equivalent). Do not reference issues or MRs by number alone — always use their title as the link text. Do NOT attribute any action to a named individual. Do not say who merged, fixed, reviewed, authored, or opened anything. The "Author" and "Assigned" labels in the data are context only — never surface them as "X did Y". Describe the work itself in the passive voice (e.g. "the provider refactor was merged"), not the person who did it. The author of a merge request is often not the person who completed or merged the work, so naming them is misleading. End your section with a single line listing the people who were active this period, exactly in this form (plain text, no ): "Contributors: Juan Correa (jucs7), Kristen Pol (kepol)". Use only the names from that list, verbatim, keeping any trailing "[N]" commit count exactly as shown. Do not introduce any other names. Format your response as an HTML fragment. Start with
Context Control Center (CCC)
then use
,
,
/
, and as needed. Output only the HTML fragment with no surrounding , , or
tags. After the project summary prose, add a single subsection titled "
How can I help on this project?
" aimed at a non-technical executive. Suggest 2-3 concrete, high-level ways a leader could support or unblock progress (e.g. resourcing, stakeholder alignment, decision-making, funding, advocacy). Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, verify it against the issue data. Do not suggest actions that are already in progress or covered by an existing MR — for example, do not suggest that work needs to be started if an issue already has a Related MR. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Gather CCC contribution stats for code and non-code contributions for release notes](https://git.drupalcode.org/project/ai_context/-/work_items/3586222) State: closed | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: unassigned | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 13 Description: ## Problem/motivation The current tools for generating release notes are inadequate as they only focus on code commits. They also require the issue number to be in the commit message. I want to gather the stats for all contributors for a release including non-code contributions which there are many. ## Solution The result for release notes should be something like: ``` New Features * #12345678 (with link) * #12345678 (with link) * ... Bug Fixes * #12345678 (with link) * #12345678 (with link) * ... Other Contributions * Plan = [number] * Task = [number] * Support = [number] Contributor… ### [Reserve pre-RC1 entity schema fields for CCC](https://git.drupalcode.org/project/ai_context/-/work_items/3586161) State: closed | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: unassigned | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 10 Related MRs (already exist for this issue — check state before suggesting new contributions): - MR !133 [Issue #3586161: Add entity schema fields.](https://git.drupalcode.org/project/ai_context/-/merge_requests/133) | State: closed | Author: Kristen Pol (kepol), 371 diff lines Description: Follow up to: #3582504 _**NOTE: Before working on this issue, verify it's still relevant and makes sense.**_ **Description:** Some future features need entity fields that are easiest to reserve before stable schema settles. Adding the fields now avoids extra update hooks later while introducing little or no UI or behavior change. This issue covers schema-only reservations from the CCC context engineering recommendations, plus related pre-RC1 schema reservations referenced by the RC1 impact analysis. **Scope:** - Add `review_by` nullable datetime field to `AiContextItem`. - Add `auto_exp… ### [Create CCC beta3 release](https://git.drupalcode.org/project/ai_context/-/work_items/3586295) State: opened | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: Kristen Pol (kepol) | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 13 Description: ### Problem/Motivation Blocked by: #3586296+s Create CCC beta3 release. Tag: `1.0.0-beta3` ### Proposed resolution Create the release once at least the must-haves are done here: - #3586182+s - [beta3 milestone](https://git.drupalcode.org/project/ai_context/-/milestones/5#tab-issues) ### Target date or deadline 6 July 2026 ### Remaining tasks - Wait on must-haves - Tag code - Create the release in UI - Celebrate! ### AI usage (if applicable) - [ ] AI Assisted Issue This issue was generated with AI assistance, but was reviewed and refined by the creator. - [ ] AI Assisted Code … ### [Create a CCC release process and template](https://git.drupalcode.org/project/ai_context/-/work_items/3586321) State: opened | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: Kristen Pol (kepol) | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 13 Description: ## Problem/motivation There are a number of steps that need to happen for a release, including gathering all the contributor information (individuals and organizations) for the release notes. ## Solution Create a step-by-step process that can be turned into an issue template. It should include any tools that are used for the release notes and other steps. ### [Clean up CCC form and table accessibility cleanup](https://git.drupalcode.org/project/ai_context/-/work_items/3586304) State: opened | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: unassigned | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 13 Related MRs (already exist for this issue — check state before suggesting new contributions): - MR !205 [Issue #3586304: Clean up CCC form and table accessibility cleanup](https://git.drupalcode.org/project/ai_context/-/merge_requests/205) | State: opened | Author: Juan Correa (jucs7), 216 diff lines Description: ## Problem/motivation Follow-up to: #3586258+s Parent: #3586298+s _**Verify the issue problem and solution before proceeding.**_ **5. Form And Table Accessibility Cleanup** **Priority:** Medium **Why group these together:** These are smaller Form API and admin UI accessibility improvements. They can be handled in one cleanup issue. Includes: - `Drupal.announce()` result counts for both JS filters. - Tests for filter announcements if feasible. ## Solution ### 5.1 Replace disabled read-only selects with text **File:** - `src/Form/AiContextAgentForm.php` **Problem:** Read-only s… ### [Allow subcontext scope to override parent scope](https://git.drupalcode.org/project/ai_context/-/work_items/3586218) State: opened | Updated: 2026-07-05 | Author: Kristen Pol (kepol) | Assigned: unassigned | Labels: AI Context Management, AI Initiative Sprint, AI Innovation, AI Sprint 10 Description: ## Problem/motivation Follow-up to: #3576092 ## Solution From the other issue: Discussion with Emma+Aidan at UX sync: - Toggle (true/false) is defaulted to "Same as parent" (true) right above Global and then hide all of them - Description: "Disable to customize scope." Here's a [plan from cursor](https://www.drupal.org/files/issues/2026-04-21/subcontext_scope_inheritance_51216439.plan_.md) that can be updated to reflect ^ ## Tasks - [x] Add code - [x] Review code - [ ] Manually test code ## AI usage - [ ] AI assisted issue - [ ] AI assisted code - [x] AI generated code --- MERGE REQUESTS (24h) --- ### [Issue #3586251: Update subcontext feature help text and docs.](https://git.drupalcode.org/project/ai_context/-/merge_requests/169) State: merged 2026-06-20 | Author: Kristen Pol (kepol) | Branch: 3586251-issue-branch | 423 diff lines Description: Closes #3586251 --- COMMITS (24h) --- (none) ======================================================================== ## [12] summariseModule:ai_related_content:executive ======================================================================== You are a technical writer producing a newsletter section about recent Drupal module activity. Module: AI Related Content (machine name: ai_related_content) Reporting period: last 24h (2026-07-05T05:00:07+00:00 to 2026-07-06T05:00:07+00:00) You are writing for a non-technical executive audience (CEO/leadership level). Focus on: business impact, strategic progress, risks, and what is being delivered. Avoid technical jargon. Do not mention branch names, function names, or API details. Explain what each piece of work means for users or the project's goals. Keep risk language proportionate to the stage of the software. For alpha or beta modules, unassigned bugs or open issues are normal and expected — do not describe them as 'reputational risks' or use alarmist framing. Reserve strong risk language for issues that are genuinely critical or blocking a stable release. Focus your report on activity that occurred within the reporting period (comments, MRs merged, commits pushed, status changes). Use the issue description to understand what each issue is about and provide context, but do not report on the description itself as news — it is background information only. Do not list every issue/MR individually — synthesise into prose. Keep it under 200 words. Do not use emoticons or mdashes. Do not wrap usernames or contributor names in tags — mention them as plain text. When mentioning a specific issue or MR, always hyperlink it using the URL provided in the data (e.g. Issue Title or the Markdown equivalent). Do not reference issues or MRs by number alone — always use their title as the link text. Do NOT attribute any action to a named individual. Do not say who merged, fixed, reviewed, authored, or opened anything. The "Author" and "Assigned" labels in the data are context only — never surface them as "X did Y". Describe the work itself in the passive voice (e.g. "the provider refactor was merged"), not the person who did it. The author of a merge request is often not the person who completed or merged the work, so naming them is misleading. End your section with a single line listing the people who were active this period, exactly in this form (plain text, no ): "Contributors: Scott Euser (scotteuser) [1]". Use only the names from that list, verbatim, keeping any trailing "[N]" commit count exactly as shown. Do not introduce any other names. Format your response as an HTML fragment. Start with
AI Related Content
then use
,
,
/
, and as needed. Output only the HTML fragment with no surrounding , , or
tags. After the project summary prose, add a single subsection titled "
How can I help on this project?
" aimed at a non-technical executive. Suggest 2-3 concrete, high-level ways a leader could support or unblock progress (e.g. resourcing, stakeholder alignment, decision-making, funding, advocacy). Keep it under 60 words. Do not add any other 'How can I help' text anywhere else in the section. CRITICAL: Before writing each suggestion, verify it against the issue data. Do not suggest actions that are already in progress or covered by an existing MR — for example, do not suggest that work needs to be started if an issue already has a Related MR. --- ISSUES UPDATED IN LAST 24h --- Each issue includes its description (for context) and the most recent comments from the last 24h (or last 5 if fewer than 5 occurred in that window). ### [Drupal 10 compatibility](https://git.drupalcode.org/project/ai_related_content/-/work_items/3576580) State: opened | Updated: 2026-07-06 | Author: Scott Euser (scotteuser) | Assigned: Scott Euser (scotteuser) | Labels: Related MRs (already exist for this issue — check state before suggesting new contributions): - MR !29 [Resolve "Drupal 10 compatibility" 2x](https://git.drupalcode.org/project/ai_related_content/-/merge_requests/29) | State: opened | Author: Scott Euser (scotteuser), 64 diff lines Description: ## Summary Need legacy hooks ### [Access checks hardening prior to stable](https://git.drupalcode.org/project/ai_related_content/-/work_items/3576579) State: closed | Updated: 2026-07-05 | Author: Scott Euser (scotteuser) | Assigned: Scott Euser (scotteuser) | Labels: Related MRs (already exist for this issue — check state before suggesting new contributions): - MR !27 [Resolve "Access checks hardening prior to stable" 2x](https://git.drupalcode.org/project/ai_related_content/-/merge_requests/27) | State: merged 2026-07-05 | Author: Scott Euser (scotteuser), 572 diff lines Description: ## Description More warnings about how to configure the Search API best --- MERGE REQUESTS (24h) --- ### [Resolve "Drupal 10 compatibility" 1x](https://git.drupalcode.org/project/ai_related_content/-/merge_requests/28) State: merged 2026-07-06 | Author: Scott Euser (scotteuser) | Branch: 3576580-drupal-10-compatibility-1x | 64 diff lines Description: Closes #3576580 ### [Resolve "Access checks hardening prior to stable" 1x](https://git.drupalcode.org/project/ai_related_content/-/merge_requests/26) State: merged 2026-07-05 | Author: Scott Euser (scotteuser) | Branch: 3576579-access-checks-hardening-1.x | 439 diff lines Description: Closes #3576579 --- COMMITS (24h) --- - [e7b57f0d](https://git.drupalcode.org/project/ai_related_content/-/commit/e7b57f0ddb157e95848343404c773525352d4e0a) fix: #3576579 Access checks hardening prior to stable — Scott Euser (2026-07-05T05:21:40.000+00:00) ======================================================================== ## [13] generateTldr:executive ======================================================================== You are an editor distilling a Drupal AI project newsletter into its most important highlights. You are writing for a non-technical executive audience. Focus on business impact, strategic progress, and delivery milestones. Avoid all technical jargon. Read all the module summaries below. Separate the highlights into two categories: - SHIPPED: things that were merged, fixed, released, or completed during this period. - ONGOING: things that are actively in progress, under review, or blocked. Be specific — name the module, what happened, and why it matters. Do not use emoticons or mdashes. Do not include any text outside the two sections. When you mention a specific issue or merge request, add an inline citation using [N] where N is the reference number from the list below. You may cite multiple references per item, e.g. [1][3]. Place citations immediately after the relevant phrase, before any punctuation. Format as two HTML sections. Use exactly this structure (all
elements must be inside the
, never outside it):
Shipped

Title here — One sentence explanation [1].

Another title — One sentence explanation.

Ongoing

Title here — One sentence explanation [2].

Up to 5 items per section. Do not output any text, tags, or characters outside these two sections. Output only the HTML fragment, no surrounding tags. --- REFERENCE LIST --- [1] Add a setup-guardrails agent skill to configure guardrails, guardrail sets, and global guardrails (ai, Issue) — https://git.drupalcode.org/project/ai/-/work_items/3586561 [2] Add a configure-ai-settings agent skill for general AI settings (default models, providers, timeout, trusted domains) (ai, Issue) — https://git.drupalcode.org/project/ai/-/work_items/3586562 [3] Add an AI reranking processor for Search API (owned by the AI module) (ai, Issue) — https://git.drupalcode.org/project/ai/-/work_items/3586543 [4] 3581952 add free-form metadata bag on InputInterface; seed pre/post/streaming... (ai, MR) — https://git.drupalcode.org/project/ai/-/merge_requests/1469 [5] Add ECA execute action for Image Classification (ai_integration_eca, Issue) — https://git.drupalcode.org/project/ai_integration_eca/-/work_items/3585003 [6] Dependency Dashboard (canvas, Issue) — https://git.drupalcode.org/project/canvas/-/work_items/3591657 [7] fix(deps): update npm minor and patch (canvas, MR) — https://git.drupalcode.org/project/canvas/-/merge_requests/1238 [8] Draft: Stage Canvas autosaves in a dedicated Workspace (canvas, MR) — https://git.drupalcode.org/project/canvas/-/merge_requests/1056 [9] Fix high level translation settings experience for Canvas (canvas, MR) — https://git.drupalcode.org/project/canvas/-/merge_requests/1303 [10] Gather CCC contribution stats for code and non-code contributions for release notes (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586222 [11] Reserve pre-RC1 entity schema fields for CCC (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586161 [12] Create CCC beta3 release (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586295 [13] Create a CCC release process and template (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586321 [14] Clean up CCC form and table accessibility cleanup (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586304 [15] Allow subcontext scope to override parent scope (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586218 [16] Issue #3586161: Add entity schema fields. (ai_context, MR) — https://git.drupalcode.org/project/ai_context/-/merge_requests/133 [17] Issue #3586251: Update subcontext feature help text and docs. (ai_context, MR) — https://git.drupalcode.org/project/ai_context/-/merge_requests/169 [18] Issue #3586304: Clean up CCC form and table accessibility cleanup (ai_context, MR) — https://git.drupalcode.org/project/ai_context/-/merge_requests/205 [19] Drupal 10 compatibility (ai_related_content, Issue) — https://git.drupalcode.org/project/ai_related_content/-/work_items/3576580 [20] Access checks hardening prior to stable (ai_related_content, Issue) — https://git.drupalcode.org/project/ai_related_content/-/work_items/3576579 [21] Resolve "Drupal 10 compatibility" 2x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/29 [22] Resolve "Drupal 10 compatibility" 1x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/28 [23] Resolve "Access checks hardening prior to stable" 1x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/26 [24] Resolve "Access checks hardening prior to stable" 2x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/27 --- MODULE SUMMARIES ---
AI (Artificial Intelligence)

Development activity this period focused on expanding the module's agent-driven automation capabilities and semantic search features. Three new feature proposals were opened, signaling continued investment in making AI functionality easier to configure and more powerful for end users.

Two related automation tasks were defined to allow the system to configure itself through conversational commands rather than manual administration. The first, Add a setup-guardrails agent skill, would enable automated configuration of safety controls and content filters. The second, Add a configure-ai-settings agent skill, would allow general system settings—such as which AI providers and models to use—to be managed through agent commands. Together these would reduce the manual overhead of deploying and maintaining AI-powered features.

A third proposal, Add an AI reranking processor for Search API, aims to improve search precision by re-ordering results using dedicated ranking models, making the feature available to the broader Drupal search ecosystem rather than a single module.

Work also continued on the module's event system, with a merge request in progress to support richer metadata and event hooks during AI operations.

How can I help on this project?

Confirm strategic priority for agent-driven configuration features relative to other roadmap items, so engineering effort can be sequenced appropriately.

Identify pilot users or partners who could validate the search reranking feature once development begins.

Contributors: Alphons Jaimon (AJV009)
---
AI Integration - ECA

This module connects AI capabilities to Drupal's Event-Condition-Action (ECA) automation framework, allowing site workflows to trigger AI operations without custom code.

During this period, work began on extending the module's automation coverage. A new task was opened to add support for image classification workflows. Currently, the module supports automating text-based AI operations such as chat, content moderation, and speech conversion. The new work will allow non-technical site builders to create automated workflows that classify or tag images using AI, for example automatically categorising uploaded photos or detecting content in user-submitted images. This expands the range of business processes that can be automated through the platform's visual workflow builder.

The module is progressing toward its 1.0.0 release. An open task during early development is normal and does not indicate delivery risk.

How can I help on this project?

Confirm whether image classification automation is a priority for the 1.0.0 roadmap or can be deferred to a later release.

Identify internal use cases or customer workflows that would benefit from automated image processing to help validate requirements.

---
Drupal Canvas

Activity over the past 24 hours focused on dependency maintenance and user experience improvements for multilingual capabilities.

A merge request was opened to update several accessibility and build tool dependencies to their latest versions, keeping the project current with external libraries. Separately, work continued on Stage Canvas autosaves in a dedicated Workspace, a substantial effort to improve how draft content is handled. Additionally, a new merge request addresses Fix high level translation settings experience for Canvas, aimed at clarifying how translation and language settings work for users.

The automated dependency tracking system flagged configuration warnings related to rate limits and authentication tokens for external services. These do not impact core functionality but may slow down automated maintenance processes if unresolved.

Overall, progress remains steady with ongoing refinements to content workflows and translation features, alongside routine maintenance to keep dependencies secure and up to date.

How can I help on this project?

Review and prioritize the pending merge requests on workspace autosaving and translation settings to accelerate user-facing improvements.

Allocate resources to configure service authentication tokens, which will streamline automated dependency updates and reduce maintenance overhead.

Contributors: **** (project_19391_bot_cb443e60680723bba08a5351bf595251), Gábor Hojtsy (goba), Lauri Timmanee (lauriii)
---
Context Control Center (CCC)

Progress continued toward the beta3 release, which is planned for completion by July 6th. Work focused on release preparation and improving the user interface for better accessibility.

Several pre-release tasks were completed, including the reservation of database schema fields needed for future features and the gathering of contribution statistics for release notes. The project is now tracking both code and non-code contributions to properly recognize all participants in the release documentation. A formal release process and template is being created to standardize future releases.

Development work is underway on accessibility improvements for forms and tables, including better screen reader support for filtered lists. Separately, work continues on allowing subcontexts to override parent scope settings, giving administrators more granular control over how context hierarchies behave.

The beta3 release itself remains open, awaiting completion of must-have items before final packaging.

How can I help on this project?

Ensure testing resources are available to validate the beta3 release before the July 6th deadline, particularly for the accessibility improvements already in development.

Consider whether formal documentation resources are needed to complement the new release process being created.

Contributors: Juan Correa (jucs7), Kristen Pol (kepol)
---
AI Related Content

The AI Related Content module made significant progress toward platform compatibility and security hardening during this period. Work was completed to ensure compatibility with Drupal 10, broadening the potential user base and extending the module's lifecycle as the Drupal ecosystem evolves. This compatibility update was merged and positions the module to serve organizations running current platform versions.

Security and configuration guidance were also strengthened through Access checks hardening prior to stable. This work added clearer warnings and best practice guidance around Search API configuration, helping site administrators deploy the module more securely and avoid common misconfigurations. This issue was closed after the related changes were merged.

These updates reflect preparation for a stable release, focusing on compatibility, security, and user guidance—key factors for adoption in production environments.

How can I help on this project?

Prioritize testing and feedback cycles to validate the Drupal 10 compatibility work in real-world scenarios before stable release.

Consider allocating resources for documentation updates that communicate the security hardening improvements to potential users and site administrators.

Contributors: Scott Euser (scotteuser) [1] ======================================================================== ## [14] factcheck:tldr:executive ======================================================================== Layer-1 corrections: 1 Judge flags: 3 ======================================================================== ## [15] generate2026Capabilities ======================================================================== You are an editor writing a strategic section for a non-technical executive audience. The Drupal AI initiative has 8 planned capabilities for 2026. Your task is to read the module activity summaries below and explain how today's progress moves each capability forward — or note where there was no relevant progress today. Be concise and direct. Focus on what matters to a business leader: is progress happening, what is the next milestone, and are there any risks? When you describe progress on a capability, add inline citations using [N] where N is the reference number from the list below. You may cite multiple references per item, e.g. [1][3]. Place citations at the end of the relevant sentence, before the closing punctuation. Output an HTML fragment using exactly this structure:
2026 Capabilities Progress

Capability name — One or two sentences on how today's activity relates to this goal, or "No direct progress today" if nothing relevant occurred.

Use only the 8 capabilities listed below, in the same order. Do not add, remove, or rename them. Do not output any text outside the
and
tags. --- 2026 CAPABILITIES --- 1. Page generation — Describe what you need and get a usable page, built from your actual design system components 2. Context management — A central place to define brand voice, style guides, audience profiles, and governance rules that AI can use 3. Background agents — AI that works without being prompted, responding to triggers and schedules while respecting editorial workflows 4. Design system integration — AI that builds with your components and can propose new ones when needed 5. Content creation and discovery — Smarter search, AI-powered optimization, and content drafting assistance 6. Advanced governance — Batch approvals, branch-based versioning, and comprehensive audit trails for AI changes 7. Intelligent website improvements — AI that learns from performance data, proposes concrete changes, and gets smarter over time through editorial review 8. Multi-channel campaigns — Create content for websites, social, email, and automation platforms from a single campaign goal --- REFERENCE LIST --- [1] Add a setup-guardrails agent skill to configure guardrails, guardrail sets, and global guardrails (ai, Issue) — https://git.drupalcode.org/project/ai/-/work_items/3586561 [2] Add a configure-ai-settings agent skill for general AI settings (default models, providers, timeout, trusted domains) (ai, Issue) — https://git.drupalcode.org/project/ai/-/work_items/3586562 [3] Add an AI reranking processor for Search API (owned by the AI module) (ai, Issue) — https://git.drupalcode.org/project/ai/-/work_items/3586543 [4] 3581952 add free-form metadata bag on InputInterface; seed pre/post/streaming... (ai, MR) — https://git.drupalcode.org/project/ai/-/merge_requests/1469 [5] Add ECA execute action for Image Classification (ai_integration_eca, Issue) — https://git.drupalcode.org/project/ai_integration_eca/-/work_items/3585003 [6] Dependency Dashboard (canvas, Issue) — https://git.drupalcode.org/project/canvas/-/work_items/3591657 [7] fix(deps): update npm minor and patch (canvas, MR) — https://git.drupalcode.org/project/canvas/-/merge_requests/1238 [8] Draft: Stage Canvas autosaves in a dedicated Workspace (canvas, MR) — https://git.drupalcode.org/project/canvas/-/merge_requests/1056 [9] Fix high level translation settings experience for Canvas (canvas, MR) — https://git.drupalcode.org/project/canvas/-/merge_requests/1303 [10] Gather CCC contribution stats for code and non-code contributions for release notes (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586222 [11] Reserve pre-RC1 entity schema fields for CCC (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586161 [12] Create CCC beta3 release (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586295 [13] Create a CCC release process and template (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586321 [14] Clean up CCC form and table accessibility cleanup (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586304 [15] Allow subcontext scope to override parent scope (ai_context, Issue) — https://git.drupalcode.org/project/ai_context/-/work_items/3586218 [16] Issue #3586161: Add entity schema fields. (ai_context, MR) — https://git.drupalcode.org/project/ai_context/-/merge_requests/133 [17] Issue #3586251: Update subcontext feature help text and docs. (ai_context, MR) — https://git.drupalcode.org/project/ai_context/-/merge_requests/169 [18] Issue #3586304: Clean up CCC form and table accessibility cleanup (ai_context, MR) — https://git.drupalcode.org/project/ai_context/-/merge_requests/205 [19] Drupal 10 compatibility (ai_related_content, Issue) — https://git.drupalcode.org/project/ai_related_content/-/work_items/3576580 [20] Access checks hardening prior to stable (ai_related_content, Issue) — https://git.drupalcode.org/project/ai_related_content/-/work_items/3576579 [21] Resolve "Drupal 10 compatibility" 2x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/29 [22] Resolve "Drupal 10 compatibility" 1x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/28 [23] Resolve "Access checks hardening prior to stable" 1x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/26 [24] Resolve "Access checks hardening prior to stable" 2x (ai_related_content, MR) — https://git.drupalcode.org/project/ai_related_content/-/merge_requests/27 --- TODAY'S MODULE SUMMARIES ---
AI (Artificial Intelligence)

Development activity this period focused on expanding the module's agent-driven automation capabilities and semantic search features. Three new feature proposals were opened, signaling continued investment in making AI functionality easier to configure and more powerful for end users.

Two related automation tasks were defined to allow the system to configure itself through conversational commands rather than manual administration. The first, Add a setup-guardrails agent skill, would enable automated configuration of safety controls and content filters. The second, Add a configure-ai-settings agent skill, would allow general system settings—such as which AI providers and models to use—to be managed through agent commands. Together these would reduce the manual overhead of deploying and maintaining AI-powered features.

A third proposal, Add an AI reranking processor for Search API, aims to improve search precision by re-ordering results using dedicated ranking models, making the feature available to the broader Drupal search ecosystem rather than a single module.

Work also continued on the module's event system, with a merge request in progress to support richer metadata and event hooks during AI operations.

How can I help on this project?

Confirm strategic priority for agent-driven configuration features relative to other roadmap items, so engineering effort can be sequenced appropriately.

Identify pilot users or partners who could validate the search reranking feature once development begins.

Contributors: Alphons Jaimon (AJV009)
---
AI Integration - ECA

This module connects AI capabilities to Drupal's Event-Condition-Action (ECA) automation framework, allowing site workflows to trigger AI operations without custom code.

During this period, work began on extending the module's automation coverage. A new task was opened to add support for image classification workflows. Currently, the module supports automating text-based AI operations such as chat, content moderation, and speech conversion. The new work will allow non-technical site builders to create automated workflows that classify or tag images using AI, for example automatically categorising uploaded photos or detecting content in user-submitted images. This expands the range of business processes that can be automated through the platform's visual workflow builder.

The module is progressing toward its 1.0.0 release. An open task during early development is normal and does not indicate delivery risk.

How can I help on this project?

Confirm whether image classification automation is a priority for the 1.0.0 roadmap or can be deferred to a later release.

Identify internal use cases or customer workflows that would benefit from automated image processing to help validate requirements.

---
Drupal Canvas

Activity over the past 24 hours focused on dependency maintenance and user experience improvements for multilingual capabilities.

A merge request was opened to update several accessibility and build tool dependencies to their latest versions, keeping the project current with external libraries. Separately, work continued on Stage Canvas autosaves in a dedicated Workspace, a substantial effort to improve how draft content is handled. Additionally, a new merge request addresses Fix high level translation settings experience for Canvas, aimed at clarifying how translation and language settings work for users.

The automated dependency tracking system flagged configuration warnings related to rate limits and authentication tokens for external services. These do not impact core functionality but may slow down automated maintenance processes if unresolved.

Overall, progress remains steady with ongoing refinements to content workflows and translation features, alongside routine maintenance to keep dependencies secure and up to date.

How can I help on this project?

Review and prioritize the pending merge requests on workspace autosaving and translation settings to accelerate user-facing improvements.

Allocate resources to configure service authentication tokens, which will streamline automated dependency updates and reduce maintenance overhead.

Contributors: **** (project_19391_bot_cb443e60680723bba08a5351bf595251), Gábor Hojtsy (goba), Lauri Timmanee (lauriii)
---
Context Control Center (CCC)

Progress continued toward the beta3 release, which is planned for completion by July 6th. Work focused on release preparation and improving the user interface for better accessibility.

Several pre-release tasks were completed, including the reservation of database schema fields needed for future features and the gathering of contribution statistics for release notes. The project is now tracking both code and non-code contributions to properly recognize all participants in the release documentation. A formal release process and template is being created to standardize future releases.

Development work is underway on accessibility improvements for forms and tables, including better screen reader support for filtered lists. Separately, work continues on allowing subcontexts to override parent scope settings, giving administrators more granular control over how context hierarchies behave.

The beta3 release itself remains open, awaiting completion of must-have items before final packaging.

How can I help on this project?

Ensure testing resources are available to validate the beta3 release before the July 6th deadline, particularly for the accessibility improvements already in development.

Consider whether formal documentation resources are needed to complement the new release process being created.

Contributors: Juan Correa (jucs7), Kristen Pol (kepol)
---
AI Related Content

The AI Related Content module made significant progress toward platform compatibility and security hardening during this period. Work was completed to ensure compatibility with Drupal 10, broadening the potential user base and extending the module's lifecycle as the Drupal ecosystem evolves. This compatibility update was merged and positions the module to serve organizations running current platform versions.

Security and configuration guidance were also strengthened through Access checks hardening prior to stable. This work added clearer warnings and best practice guidance around Search API configuration, helping site administrators deploy the module more securely and avoid common misconfigurations. This issue was closed after the related changes were merged.

These updates reflect preparation for a stable release, focusing on compatibility, security, and user guidance—key factors for adoption in production environments.

How can I help on this project?

Prioritize testing and feedback cycles to validate the Drupal 10 compatibility work in real-world scenarios before stable release.

Consider allocating resources for documentation updates that communicate the security hardening improvements to potential users and site administrators.

Contributors: Scott Euser (scotteuser) [1] ======================================================================== ## [16] factcheck:capabilities:executive ======================================================================== Layer-1 corrections: 0 Judge flags: 2