dial-docs
Skill501 starsChanged 15 days agoApache-2.0View on GitHub
On-demand index of the AI DIAL Chat design docs in docs/. Use when you need ground-truth on how the app works or is built — overall architecture, technical/product requirements, the authentication subsystem (login, logout, OIDC, session cookies, encrypted session, transparent token refresh, BFF auth flow, SessionGuard), theme customization and color tokens, embedding the chat through the overlay, the Responses API integration, MCP Apps (tool UI resources, inline preview/canvas, sandbox proxy), adopting the reusable chat workflows (skill import, file attachment, prompt selector) in another host, or environment-variable migration. Resolves to the one relevant doc; do not preload all of them.
- Reads credentials
In this repository59 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/a11y.mdcCursor rule
- nx-generateSkill
- nx-importSkill
- nx-pluginsSkill
- nx-run-tasksSkill
- nx-workspaceSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- address-current-branch-reviewSkill
- api-designSkill
- celebration-scene-ideasSkill
- code-review-and-qualitySkill
- create-ticketSkill
- dep-scanSkill
- dep-triageSkill
- extract-to-libSkill
- figmaSkill
- fix-cve-backportSkill
- git-shipSkill
- i18n-stringsSkill
- lean-verificationSkill
- lib-themingSkill
- monitor-ciSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- proactive-security-monitorSkill
- refactoring-auditSkill
- chat-release-notesSkill
- responsive-designSkill
- security-monitor-triagerSkill
- snyk-jira-ingestSkill
- snyk-scan-stubSkill
- snyk-triageSkill
- ui-kit-reviewSkill
- nx-generateSkill
- nx-pluginsSkill
- nx-run-tasksSkill
- nx-workspaceSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
- nx-generateSkill
- nx-importSkill
- nx-pluginsSkill
- nx-run-tasksSkill
- nx-workspaceSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
The file
Files
DIAL Docs
Ground-truth design docs live in docs/. This skill is the index. Open only the doc that matches your task — don't read all of them.
Index
| Doc | Read it when |
docs/architecture.md | Orienting on the overall app: structure, layers, major decisions. |
docs/technical-requirements.md | You need the product/technical requirements behind a feature. |
docs/auth/auth-bff-encrypted-cookie.md | Changing the auth flow: stateless BFF, OIDC login/callback, encrypted session cookie, transparent refresh, federated logout, cross-pod stateless decryption. |
docs/auth/testing-current-auth-implementation.md | Writing or running auth tests: what exists today (GET /api/v1/auth/me, global SessionGuard, refresh) and how to exercise it. |
docs/auth/auth-diagrams/ | You need the picture: Mermaid .mmd + .svg for architecture, provider registry, login, refresh, logout, cross-pod, cookie structure. |
docs/legacy-chat-migration-guide.md | Moving a deployment from the legacy DIAL Chat (0.x) to 1.0: what changed, the checklist, and the legacy → new environment-variable mapping. |
docs/theme-customization.md | Theming: the themes service and config.json format, the color tokens the app reads, logos and favicon, the light/dark/system picker, legacy theme migration. |
docs/chat-overlay-migration-guide.md | Embedding the chat: the overlay package, postMessage protocol and handshake, OverlayFeature flags, and migrating from the legacy @epam/ai-dial-overlay. |
docs/custom-viewers.md | Working on Custom Viewers: an application's own iframe page replacing the conversation view — configuration, query params, the data sent, the events handled, sandbox limits. |
docs/mcp-apps.md | Working on MCP Apps: tool discovery, message matching, the inline preview and canvas, the BFF proxy endpoints, the separate-origin sandbox, caching, deployment, known limits. |
docs/responses-api-integration.md | Working on completions dispatch: how deployments declaring responses_api are routed and normalized. |
docs/observability.md | Configuring OpenTelemetry, interpreting HTTP/generation/runtime metrics, importing Grafana dashboards, or troubleshooting missing telemetry. |
docs/host-install-matrix.md | An embedding host asks what to put in its own package.json for a given set of libs. Generated from the manifests; do not hand-edit. |
docs/reusable-chat-workflows.md | Adopting the reusable skill-import, file-attachment or prompt-selector workflows in another chat host: public imports, what the host keeps, release alignment, and what the packed fixtures do and do not prove. |
docs/projects-reuse.md | Building the Projects pages in another host: which project requests and hooks come from @epam/ai-dial-chat-hooks/project, which components from @epam/ai-dial-projects, and what the host keeps. |
apps/chat-api/README.md | The full environment-variable reference: every supported variable, its default, and its effect. apps/chat-api/.env.template is the annotated source. |
How to use
- Match your task to a row above and open that one doc.
- For auth work, start with
auth-bff-encrypted-cookie.md; use the diagrams for flow detail.
Maintaining the index
Adding a doc to docs/ means adding a row here in the same change — an unindexed doc is one nobody finds. docs/architecture.md additionally has a standing update obligation (new lib, app, backend domain, context, route, or endpoint group); see the Docs section of AGENTS.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.