spec, typespec authoring, update the design doc to reflect the latest design#16233
Open
haolingdong-msft wants to merge 4 commits into
Open
spec, typespec authoring, update the design doc to reflect the latest design#16233haolingdong-msft wants to merge 4 commits into
haolingdong-msft wants to merge 4 commits into
Conversation
github-actions
Bot
added
azsdk-cli
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
….com/Azure/azure-sdk-tools into update-typespec-authoring-design-doc
haolingdong-msft
changed the title
Contributor
There was a problem hiding this comment.
Pull request overview
This PR updates the TypeSpec authoring design spec to reflect the current architecture decision: moving away from a standalone custom agent and standardizing on the azure-typespec-author GitHub Copilot Skill, along with an updated architecture diagram.
Changes:
- Updates the “Azure TypeSpec Style Guide” reference link.
- Rewrites the design proposal section to describe the skill-based workflow (steps, plan sources, validation, rationale) instead of the prior custom-agent approaches.
- Adds/updates the architecture diagram reference for the skill design.
|
|
||
| #### Architecture | ||
|
|
||
|  |
Comment on lines
+266
to
+269
| Step 3 builds the authoring plan from two grounding sources; when their guidance conflicts, agentic search wins: | ||
|
|
||
| The TypeSpec authoring workflow follows a streamlined process where the user interacts with Custom agent `azure-typespec-author-agent` using natural language, and agent leverages the TypeSpec Solution Tool (MCP) to generate standards-compliant solutions. The architecture diagram above illustrates this end-to-end flow: | ||
| 1. **MCP tool** — call `azsdk_typespec_generate_authoring_plan` with the verbatim user request, the Step 1–2 context, and the project root. The tool returns a RAG-grounded plan from the Azure SDK Knowledge Base. | ||
| 2. **Agentic search** — follow `references/agentic-search.md`: select the relevant URLs from `references/reference-document-links.md`, `web_fetch` each into Markdown, search for content matching a query derived from the request and Step 1 result, iterate until sufficient, and synthesize the extracted guidance into a concrete plan. |
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Fix #15707