Repository navigation
feat: render skill invocations in the transcript and edit flow - #30881
Merged
Merged
Conversation
Add sqlc queries for skills owned by a chat project and authorize them through the parent project in dbauthz: reading needs chat_project:read and writing needs chat_project:update. Skill.RBACObject keeps denying project rows so any unwrapped path fails closed. Add the chat_project_skill audit resource type and AuditableChatProjectSkill so the upcoming project skill API can record audit entries.
Add experimental routes to list, create, read, update and delete skills on a chat project. Reading needs read on the project and writes need update; callers who lack the permission get a 404 like the project instructions routes. The handlers reuse the shared skill create and update path, map the per-project cap and name index to 409, and audit every write as a chat_project_skill. Add matching ExperimentalClient methods.
Chats in a project now get the project's enabled skills as a new "project" skill source, read as the chat owner each turn. Subagents use the root chat's project. read_skill loads project skill bodies, and MergeSkills takes sources in merge order so new sources do not change its signature.
The "/" menu offers the skills of the chat's project, next to personal, organization and workspace skills, and /clear and /compact defer to a project skill with the same name. Documents project skills.
…g in the slash menu Organization and project skills load through one hook, and the menu renders its skill groups from one ordered list. Adds project loading and error stories.
…lify skill group offsets
…nd resolve emptiness in the hook
…naming in the composer
Cover the project-only skill tool check in the integration test, the project skill body loader's not-found mapping, and the chat-projects experiment gate in the composer.
… request instead of menu markup
…ub after each test
…ed skill helpers Split the form body of SkillEditor into SkillEditorForm, settle saves through a mutate callback so the editor stays locked until the request finishes, move the read-only enabled indicator into SkillEnabledSwitch, and share the empty and loaded form value helpers in utils/skills.ts.
Add API methods and query factories to read, create, update, and delete chat project skills, a projectSkillsScope for the shared skill helpers, and ProjectSkillsDialog, which lists a project's skills and edits them with SkillEditorForm.
Add a Skills row to the project Details panel that opens ProjectSkillsDialog, with stories for the dialog and the panel, and document where project skills are managed.
Add a skill-invocation chat input and message part. chatd loads the invoked skill body with the chat owner's permissions when a message is created, sent, or edited, stores it on the part, and renders it into the user's prompt inside <invoked-skill>. Unavailable skills reject the request with a 400. The stored body is internal and never returned by the API.
… focusable and cover submit settlement
…t-skills/project-skills-dialog
…ts through refetches and handle deleted skills
…oject-skills/project-skills-details
… and toggle tests to the Details row PR
…downloads, toggles, refetches and deleted skills
…roject-skills/invocation-api
…tates the readOnly prop
…ll details after deletes and refresh after download 404s
jaaydenh
added a commit
that referenced
this pull request
Oct 21, 2026
Adds `ProjectSkillsDialog`, the dialog for managing a chat project's skills, plus the API client methods and react-query factories for the project skill routes from #30827. Nothing opens the dialog yet; the next PR adds the entry point in the project page Details panel. - List view: "Project skills" with each skill's name, description, an enabled switch and last updated time, a row menu with Edit (View when read-only), Download and Delete, and a "No skills added yet" empty state. - New and Edit replace the list inside the same dialog and reuse `SkillEditorForm`, including paste-to-import and file upload. Name is locked when editing, and Escape asks before discarding unsaved edits. - Without update permission the dialog is read-only: no New, Delete or Save, and fields are disabled. - Create, update and delete invalidate the project skill list, so the composer `/` menu picks up changes too. A 409 (duplicate name or the 100-skill cap) is shown in the form and refreshes the list. Stack (merge top to bottom): - #30826 - #30827 - #30838 - #30840 - #30854 - #30855 👈 - #30856 - #30861 - #30880 - #30881 - #30882 - #30884 - #31122
jaaydenh
added a commit
that referenced
this pull request
Oct 21, 2026
Adds a "Skills" row to the project page Details panel. It shows "None" or the skill count (noting disabled skills) and opens the project skills dialog from #30855. Editing follows the project's `permissions.update`, the same flag that gates the instructions editor. The server computes it with the project's sharing ACL, so an `admin` sharee can edit skills, and users who can only read the project get the read-only dialog. Focus returns to the row when the dialog closes. The extending agents docs now point at the project page for managing project skills. Dogfood UAT on this stack passed: creating, editing, importing, downloading, turning off and deleting skills from the dialog; Save stays disabled until the form is valid; a duplicate name shows the 409 in the dialog; new skills show up in the project page `/` menu without a reload. The read-only dialog was checked with a stubbed projects list, before project sharing (#30439) landed. | Editor | List after saving | | --- | --- | | <img alt="New project skill editor" src="https://raw.githubusercontent.com/coder/coder/assets/pr-30856-project-skills/pr/skill-editor.png" width="600" /> | <img alt="Project skills list after saving" src="https://raw.githubusercontent.com/coder/coder/assets/pr-30856-project-skills/pr/skill-list.png" width="600" /> | Stack (merge top to bottom): - #30826 - #30827 - #30838 - #30840 - #30854 - #30855 - #30856 👈 - #30861 - #30880 - #30881 - #30882 - #30884 - #31122 --------- Co-authored-by: Cursor <cursoragent@cursor.com>
…con size token for the skill chip icon
# Conflicts: # site/src/pages/AgentsPage/components/ChatMessageInput/SkillChip.tsx
Collaborator
|
Design isn't working for me, a bit clunky. added an issue to provide feedback https://linear.app/codercom/issue/DES-22217/review-and-normalize-pill-states-across-coder-agents |
jaaydenh
added a commit
that referenced
this pull request
Oct 22, 2026
Adds a structured `skill-invocation` chat part so a user message can carry an explicit skill. chatd loads that exact skill when the message is sent and puts its body into the user's prompt, so the skill always applies instead of relying on the model to notice it in `<available-skills>`. The composer chip that sends these parts comes in the next PR. - codersdk: a `skill-invocation` input part and message part with `skill_source` (`personal`, `org`, `project`, `workspace`) and `skill_name`. The resolved body is stored on the part as internal `skill_body`; it's hidden from TypeScript and stripped from every API response. - coderd rejects an unknown source or an invalid name with 400. - chatd resolves each invocation on create, send and edit with the chat owner's permissions, through the same loaders as `read_skill`: stored skills by source and name (project skills through the chat's project, with the root chat fallback for subagents) and workspace skills from the pinned context snapshot. The body is saved at send time so past turns show what the model received. A missing, disabled or unreadable skill rejects the send with 400 "Skill project/triage is not available." - The prompt renders a line saying the user invoked the skill, followed by `<invoked-skill name="project/triage">` with the sanitized body. Titles and hook prompt text show the invocation as `/project/triage`. - The site only gets no-op cases so the regenerated types compile. `coderd/x/chatd/ARCHITECTURE.md` gets a TODO for the author. Stack (merge top to bottom): - #30826 - #30827 - #30838 - #30840 - #30854 - #30855 - #30856 - #30861 👈 - #30880 - #30881 - #30882 - #30884 - #31122 - #31126 --------- Co-authored-by: Cursor <cursoragent@cursor.com>
# Conflicts: # site/src/pages/AgentsPage/AgentCreatePage/AgentCreatePage.tsx
Co-authored-by: Nick Vigilante <nickvigilante@users.noreply.github.com>
…transcript' into rs-skill-chips-transcript
Base automatically changed from
chat-project-skills/skill-chips-composer
to
main
October 22, 2026 04:43
jaaydenh
added a commit
that referenced
this pull request
Oct 22, 2026
Choosing a skill from the `/` menu now inserts a skill chip into the composer instead of `/alias` text, and the message sends it as a structured `skill-invocation` part (#30861), so chatd loads that exact skill's body into the prompt. - A Lexical `SkillInvocationNode` renders the chip with a remove button; `/clear` and `/compact` still insert as commands, and typed `/name` text that wasn't picked from the menu still goes out as plain text (#31126 turns a typed full alias into a chip). - `buildChatInputContent` emits text and skill parts in document order, a chip-only message can be sent, drafts keep chips, and the new chat form forwards them. - `insertSkill(source, name)` on the composer handle inserts a chip at the caret without duplicating one that's already there. The project action bar later in this stack uses it. - Arrow keys step over chips instead of selecting them. Selecting a chip node dropped the browser selection, so the next keystroke landed at the start of the message; file reference chips had the same bug and get the same fix. - Copy and paste keep chips: copied text includes `/source/name`, pasting skips a chip that's already in the composer, and a chip for a skill this chat can't use is pasted as plain text. Rendering the parts in the transcript and edit flow is in the next PR. Dogfood UAT passed on this stack: picking project, personal and organization skills sends one skill part each and the agent answers from the skill body without calling `read_skill`; the caret, paste and copy cases above, drafts, `/clear`, `/compact` and the 400 for a disabled or deleted skill all behaved as expected. | Chip in the composer | Sent message in the transcript | | --- | --- | | <img alt="Skill chip in the project composer" src="https://raw.githubusercontent.com/coder/coder/assets/pr-30880-skill-chips/pr/composer-chip.png" width="600" /> | <img alt="Skill chip in the sent message with the codeword reply" src="https://raw.githubusercontent.com/coder/coder/assets/pr-30880-skill-chips/pr/transcript-chip.png" width="600" /> | Stack (merge top to bottom): - #30826 - #30827 - #30838 - #30840 - #30854 - #30855 - #30856 - #30861 - #30880 👈 - #30881 - #30882 - #30884 - #31122 - #31126 --------- Co-authored-by: Cursor <cursoragent@cursor.com>
ethanndickson
approved these changes
Oct 22, 2026
ethanndickson
left a comment
Member
There was a problem hiding this comment.
Docs need cleaning up. I'd probably just not add any docs here
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Renders
skill-invocationparts from #30861 in the conversation. A user message shows its skill chips inline with the text, and a message with only a skill invocation is no longer treated as empty. Editing a past message restores its chips in the composer (the editable payload now carries the serialized editor state), optimistic edits keep skill parts, and queued messages show the skill.Stack (merge top to bottom):