AGENT SKILL

test-unbranded-emitter

Build and test the @typespec/http-client-python emitter. Use this skill whenever the user wants to test their local changes to the emitter, run the generator test suite, check if their http-client-python changes are passing, or validate a fix. Triggers on phrases like "test the emitter", "run tests", "check if my changes pass", "run test:generator", "run CI", or any mention of testing/validating changes in the emitter package.

License 许可
MIT
所属仓库
microsoft/typespec
最近更新
2026-11-14
Stars
★ 5.9k
Forks
423

01 前言 Front Matter

name
test-unbranded-emitter
description
Build and test the @typespec/http-client-python emitter. Use this skill whenever the user wants to test their local changes to the emitter, run the generator test suite, check if their http-client-python changes are passing, or validate a fix. Triggers on phrases like "test the emitter", "run tests", "check if my changes pass", "run test:generator", "run CI", or any mention of testing/validating changes in the emitter package.

03 SKILL.md 正文

Test Emitter Skill

Builds and tests @typespec/http-client-python to validate local changes. Automatically regenerates if the generated code is stale.

Paths

All paths are relative to the http-client-python package root: ~/Desktop/github/typespec/packages/http-client-python

Item Path
Package root ~/Desktop/github/typespec/packages/http-client-python
Emitter source emitter/src
Generated (unbranded) generator/test/unbranded/generated
Generated (azure) generator/test/azure/generated
Regenerate marker .last-regenerate

Workflow

Step 1: Build the emitter

cd ~/Desktop/github/typespec/packages/http-client-python
npm run build

Check for TypeScript compilation errors. If the build fails, report the errors to the user and stop — do not proceed to testing.

Step 2: Check if regeneration is needed

Regeneration is needed if ANY of these conditions are true:

  1. Generated folder doesn't exist or is empty:

    cd ~/Desktop/github/typespec/packages/http-client-python
    
    if [ ! -d "generator/test/unbranded/generated" ] \
      || [ -z "$(ls -A generator/test/unbranded/generated 2> /dev/null)" ]; then
      echo "Unbranded generated folder is empty - regeneration needed"
    fi
    
    if [ ! -d "generator/test/azure/generated" ] \
      || [ -z "$(ls -A generator/test/azure/generated 2> /dev/null)" ]; then
      echo "Azure generated folder is empty - regeneration needed"
    fi
    
  2. No regenerate marker file exists:

    if [ ! -f ".last-regenerate" ]; then
      echo "No regenerate marker - regeneration needed"
    fi
    
  3. Emitter source files are newer than the marker:

    if [ -n "$(find emitter/src -newer .last-regenerate -type f 2> /dev/null | head -1)" ]; then
      echo "Emitter source changed since last regenerate - regeneration needed"
    fi
    

Step 3: Regenerate if needed

If any condition from Step 2 is true:

cd ~/Desktop/github/typespec/packages/http-client-python
echo "Regenerating test clients..."
npm run regenerate

After successful regeneration, update the marker:

touch .last-regenerate

If regeneration fails, report the error and stop.

If regeneration is NOT needed, inform the user:

"Generated code is up to date (source unchanged since last regeneration). Skipping regenerate."

Step 4: Run the generator test suite

cd ~/Desktop/github/typespec/packages/http-client-python
npm run ci

This runs:

  1. test:emitter - vitest unit tests for the emitter
  2. ci:generator - pytest tests against generated code

The full CI can take several minutes. Keep the user informed that it's running.

Step 5: Report results

  • If tests pass: Confirm success and summarize any notable output (warnings, skipped tests, etc.)
  • If tests fail: Show the failing test names and error messages clearly. Offer to help debug or investigate specific failures.

Integration with diff-upstream

Both skills share the regeneration marker system:

  • diff-upstream always regenerates and updates .last-regenerate
  • test-unbranded-emitter checks this marker and skips regeneration if fresh

Efficient workflow:

diff-upstream → test-unbranded-emitter

The second command will skip regeneration since diff-upstream just did it.

Standalone workflow:

test-unbranded-emitter

Will regenerate only if source changed since last run.

Notes

Regeneration takes time

npm run regenerate can take 2-3 minutes. The staleness check avoids this delay when the user is iterating on test fixes (not emitter changes).

Test types

Command What it runs Duration
npm run test:emitter vitest unit tests only ~5 seconds
npm run test:generator pytest only (no vitest) ~2 minutes
npm run ci vitest + pytest (full CI) ~2-3 minutes

This skill runs npm run ci (full CI). If the user wants just unit tests or just pytest, they can ask specifically.

Known flaky test

The test server teardown sometimes fails with ProcessLookupError - this is a pre-existing infrastructure issue, not a test failure. All actual tests may pass even if you see this error at the end.

Force regeneration

If the user suspects stale generated code despite the marker, they can force regeneration:

rm ~/Desktop/github/typespec/packages/http-client-python/.last-regenerate

Then run the skill again.

Gitignore

Ensure this entry is in the package's .gitignore:

.last-regenerate

04 同仓库更多 Skills

microsoft
microsoft/typespec

generate-from-typespec

Generate Python SDK code from a TypeSpec specification using the local emitter. Use this skill when the user wants to generate/regenerate a Python client from a TypeSpec spec, provides a GitHub URL or local path to a TypeSpec project, or says things like "generate from this spec", "emit Python from this tsp", "regenerate the SDK", or "compile this TypeSpec for Python".

Skill与智能体开发
★ 5.9k
microsoft
microsoft/typespec

diff-upstream

Regenerate the local emitter and diff the generated code against the upstream baseline checked into autorest.python. Use this skill when the user wants to see how their emitter changes affect generated code compared to what's currently in production, says things like "diff upstream", "compare to baseline", "what changed vs production", "show me the diff", "how does this affect generated code", or wants to validate their changes produce the expected output differences.

Skill与智能体开发
★ 5.9k
microsoft
microsoft/typespec

writing-python-sdk-spector-mock-api-tests

Writes TypeSpec http-client-python generator mock API tests (azure/unbranded/shared) from a Spector case. Use when given a Spector case link or a PR link that modifies Spector cases under http-specs/azure-http-specs.

开发工程师内容创作者后端与接口写作与文案
★ 5.9k
microsoft
microsoft/typespec

pnpm-format

Format the codebase with pnpm and recover from common formatting failures.

★ 5.9k
microsoft
microsoft/typespec

minimal-repro

Help create a minimal reproduction for a TypeSpec compiler or emitter bug. Use when a user provides TypeSpec source (pasted code or a GitHub URL) and describes an issue. Reproduces locally and reduces to a single-file repro.

★ 5.9k
microsoft
microsoft/typespec

http-client-python-bump-and-release

Create a PR to bump TypeSpec/Azure Tools dependencies, update peer dependencies, or release a new version of the http-client-python package.

★ 5.9k