feat(ci): add cross-platform final build checks#279
Conversation
Adding .gitkeep for PR creation (default mode). This file will be removed when the task is complete. Issue: ProverCoderAI#278
konard
changed the title
Working session summaryDone. Updated existing PR 279 and marked it ready: Implemented:
Verified locally: Verified CI on latest SHA SOURCE: n/a. This summary was automatically extracted from the AI working session output. |
🤖 Solution Draft LogThis log file contains the complete execution trace of the AI solution draft process. 💰 Cost estimation:
📊 Context and tokens usage:
Total: (672.7K + 22.4M cached) input tokens, 61.0K output tokens, $31.863471 cost 🤖 Models used:
📎 Log file uploaded as Repository (83153KB)Now working session is ended, feel free to review and add any feedback on the solution draft. |
✅ Ready to mergeThis pull request is now ready to be merged:
Monitored by hive-mind with --auto-restart-until-mergeable flag |
|
в Final build надо ещё проверить что запускается browser |
|
@coderabbitai review |
✅ Actions performedReview triggered.
|
📝 WalkthroughSummary by CodeRabbit
WalkthroughThis PR establishes cross-platform support for Linux, macOS, and Windows by introducing portable executable marking, simplifying CLI scripts to remove bash wrappers, restricting git mirror refresh scope, and implementing a CI/CD workflow that validates the build across all three platforms. ChangesCross-platform build and CI pipeline
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.github/workflows/final-build.yml:
- Around line 27-33: The workflow .github/workflows/final-build.yml currently
only checks CLIs ("Verify docker-git CLI starts" and "Verify session sync CLI
starts"); add a new step after those that performs the requested browser/UI
clone smoke check by launching a headless browser and exercising the UI clone
path (open app served from the build, navigate to the clone UI/menu, trigger a
clone, and assert success). Name the step clearly (e.g., "Verify browser UI
clone smoke check") and implement it using your existing test runner or a
lightweight headless tool (Playwright/puppeteer or an npm script) so it starts
the built web app, runs the UI clone flow, and fails the job on error.
In `@packages/app/tests/docker-git/package-scripts-cross-platform.test.ts`:
- Around line 24-34: Add fast-check property-based assertions covering the same
invariants currently tested by the table-driven checks: the "no bash" invariant
for each launch script and the "no chmod" invariant for the package build
script. Use fast-check's fc.assert with an fc.property that generates indices or
script entries from the existing launchScripts array and validates that the
selected entry.script does not match /\bbash(?:\.exe)?\b/u (referencing
launchScripts and entry.scriptName/entry.packageName for contextual failure
messages), and another property that checks sessionSyncPackage.scripts.build
does not match /\bchmod\s+/u. Replace or augment the existing for-loop and
single expect with these fc.assert(fc.property(...)) calls so the test file
package-scripts-cross-platform.test.ts uses property-based testing for the
invariants.
In `@packages/lib/tests/core/templates.test.ts`:
- Around line 77-86: The test for "renderEntrypoint clone cache" is missing
negative assertions for pull-request and merge-request refspecs; update the spec
for the entrypoint returned by renderEntrypoint(makeTemplateConfig()) to assert
it does not contain the undesired refs by adding checks that entrypoint does not
contain "'+refs/pull/*:refs/pull/*'" and
"'+refs/merge-requests/*:refs/merge-requests/*'". Ensure you add these two
expect(...).not.toContain(...) assertions alongside the existing negative check
so the test prevents regressions.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: f798fdcc-08da-4eff-8545-a01201bd5aac
📒 Files selected for processing (11)
.changeset/cross-platform-final-build.md.github/actions/setup/action.yml.github/workflows/final-build.ymlpackage.jsonpackages/app/package.jsonpackages/app/src/lib/core/templates-entrypoint/tasks.tspackages/app/tests/docker-git/package-scripts-cross-platform.test.tspackages/docker-git-session-sync/package.jsonpackages/lib/src/core/templates-entrypoint/tasks.tspackages/lib/tests/core/templates.test.tsscripts/mark-executable.mjs
| - name: Build final workspace packages | ||
| run: bun run build | ||
| - name: Verify docker-git CLI starts | ||
| run: bun ./packages/app/dist/src/docker-git/main.js --help | ||
| - name: Verify session sync CLI starts | ||
| run: bun ./packages/docker-git-session-sync/dist/docker-git-session-sync.js --help | ||
| - name: Prepare package artifacts directory |
There was a problem hiding this comment.
Final Build is missing the requested browser/UI clone smoke check.
The workflow currently validates CLI startup only. It does not cover the reviewer-requested runtime path: browser launch and cloning via UI/menu, so the PR acceptance criteria in discussion remain partially unverified.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.github/workflows/final-build.yml around lines 27 - 33, The workflow
.github/workflows/final-build.yml currently only checks CLIs ("Verify docker-git
CLI starts" and "Verify session sync CLI starts"); add a new step after those
that performs the requested browser/UI clone smoke check by launching a headless
browser and exercising the UI clone path (open app served from the build,
navigate to the clone UI/menu, trigger a clone, and assert success). Name the
step clearly (e.g., "Verify browser UI clone smoke check") and implement it
using your existing test runner or a lightweight headless tool
(Playwright/puppeteer or an npm script) so it starts the built web app, runs the
UI clone flow, and fails the job on error.
| describe("package scripts cross-platform contract", () => { | ||
| it("keeps user-facing launch scripts independent from bash", () => { | ||
| for (const entry of launchScripts) { | ||
| expect(entry.script, `${entry.packageName}:${entry.scriptName}`).not.toMatch(/\bbash(?:\.exe)?\b/u) | ||
| } | ||
| }) | ||
|
|
||
| it("keeps final package build independent from raw chmod", () => { | ||
| expect(sessionSyncPackage.scripts.build).not.toMatch(/\bchmod\s+/u) | ||
| }) | ||
| }) |
There was a problem hiding this comment.
🛠️ Refactor suggestion | 🟠 Major | ⚡ Quick win
Add property-based assertions for script invariants.
This test is table-driven only; please add fast-check property tests for the bash/chmod invariants to satisfy the test policy for .test.ts files.
Proposed direction
+import fc from "fast-check"
...
+ it("bash-free launch scripts hold for all declared launch entries", () => {
+ fc.assert(
+ fc.property(fc.constantFrom(...launchScripts), (entry) => {
+ expect(entry.script).not.toMatch(/\bbash(?:\.exe)?\b/u)
+ })
+ )
+ })As per coding guidelines "**/*.test.{ts,tsx}: Implement property-based testing using fast-check for mathematical properties and invariants."
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@packages/app/tests/docker-git/package-scripts-cross-platform.test.ts` around
lines 24 - 34, Add fast-check property-based assertions covering the same
invariants currently tested by the table-driven checks: the "no bash" invariant
for each launch script and the "no chmod" invariant for the package build
script. Use fast-check's fc.assert with an fc.property that generates indices or
script entries from the existing launchScripts array and validates that the
selected entry.script does not match /\bbash(?:\.exe)?\b/u (referencing
launchScripts and entry.scriptName/entry.packageName for contextual failure
messages), and another property that checks sessionSyncPackage.scripts.build
does not match /\bchmod\s+/u. Replace or augment the existing for-loop and
single expect with these fc.assert(fc.property(...)) calls so the test file
package-scripts-cross-platform.test.ts uses property-based testing for the
invariants.
| describe("renderEntrypoint clone cache", () => { | ||
| it("refreshes mirrors without broad remote refs", () => { | ||
| const entrypoint = renderEntrypoint(makeTemplateConfig()) | ||
|
|
||
| expect(entrypoint).toContain("git --git-dir '$CACHE_REPO_DIR' fetch") | ||
| expect(entrypoint).toContain("'+refs/heads/*:refs/heads/*'") | ||
| expect(entrypoint).toContain("'+refs/tags/*:refs/tags/*'") | ||
| expect(entrypoint).not.toContain("'+refs/*:refs/*'") | ||
| }) | ||
| }) |
There was a problem hiding this comment.
🧩 Analysis chain
🌐 Web query:
What is the recommended way to run fast-check property-based tests in Vitest 4.1.5 (including TypeScript examples)?
💡 Result:
Recommended way: use fast-check through the dedicated Vitest connector package @fast-check/vitest, and run property-based “prop” tests via the connector’s enriched test/it APIs (e.g., test.prop / it.prop). This is the safest/simplest integration because the connector wires up Vitest-specific concerns like timeouts and lifecycle hooks. [1][2] Setup (TypeScript) 1) Install: - npm i -D vitest fast-check @fast-check/vitest [1] 2) Write property-based tests using @fast-check/vitest instead of importing test/it directly from vitest. The connector provides.prop variants for property inputs. Example: tuple (positional) notation ts // your-test.spec.ts import { test, expect, fc } from '@fast-check/vitest'; a function isSubstring(text: string, pattern: string) { return text.includes(pattern); } test.prop([fc.string(), fc.string(), fc.string()])( 'should detect substring', (a, b, c) => { const text = a + b + c; return expect(isSubstring(text, b)).toBe(true); }, ); Property inputs can be provided positionally with test.prop([arb1, arb2,...]). [1][2] Example: record (named) notation ts import { test, expect, fc } from '@fast-check/vitest'; function isSubstring(text: string, pattern: string) { return text.includes(pattern); } test.prop({ a: fc.string(), b: fc.string(), c: fc.string() })( 'should detect substring', ({ a, b, c }) => { const text = a + b + c; expect(isSubstring(text, b)).toBe(true); }, ); Record notation passes inputs as a named object to the predicate. [1][2] Reproducibility / replaying failures (seed) You can pass fast-check parameters (including a seed) to test.prop so failures are replayable. [2] Example (seeded run) ts import { test, expect, fc } from '@fast-check/vitest'; test.prop([fc.nat(), fc.nat()], { seed: 4242 })( 'should replay the test for the seed 4242', (a, b) => { expect(a + b === b + a).toBe(true); }, ); [2] How this relates to “fast” execution in Vitest 4.1.5 - The recommended approach is to delegate property-test orchestration to @fast-check/vitest; it takes care of Vitest integration details (timeouts and beforeEach/afterEach lifecycle wiring) so property predicates run correctly under Vitest’s execution model. [1][2] - For more extensive property testing, @fast-check/vitest supports a full property-based mode that repeatedly generates inputs to find edge cases. [2] Alternative (not recommended for Vitest): using fast-check directly fast-check itself works with any runner, but fast-check’s Vitest docs specifically recommend the connector as the “safest and simplest path” for Vitest integration, rather than using Vitest’s test/it directly. [1]
Citations:
- 1: https://fast-check.dev/docs/tutorials/setting-up-your-test-environment/property-based-testing-with-vitest/
- 2: https://www.npmjs.com/package/@fast-check/vitest
🏁 Script executed:
# First, locate the test file and examine its content
find . -path "*/packages/lib/tests/core/templates.test.ts" -type fRepository: ProverCoderAI/docker-git
Length of output: 112
🏁 Script executed:
# Check if file exists using git ls-files as fallback
git ls-files | grep -E "templates\.test\.ts"Repository: ProverCoderAI/docker-git
Length of output: 110
🏁 Script executed:
# Search for templates test file more broadly
fd "templates.test.ts" --type fRepository: ProverCoderAI/docker-git
Length of output: 110
🏁 Script executed:
# Look for the renderEntrypoint function
rg "renderEntrypoint" -t ts -t tsx -A 5 --max-count 20Repository: ProverCoderAI/docker-git
Length of output: 96
🏁 Script executed:
# Check project dependencies for Vitest and fast-check
cat package.json | jq '.devDependencies | to_entries[] | select(.key | test("vitest|fast-check")) | "\(.key): \(.value)"'Repository: ProverCoderAI/docker-git
Length of output: 50
🏁 Script executed:
# Search for existing fast-check usage in test files
fd ".test.ts" -o ".spec.ts" --type f -x rg "fast-check|fc\." {} --max-count 5Repository: ProverCoderAI/docker-git
Length of output: 204
🏁 Script executed:
# Read the test file
cat -n packages/lib/tests/core/templates.test.ts | head -100Repository: ProverCoderAI/docker-git
Length of output: 5439
🏁 Script executed:
# Search for renderEntrypoint function definition
rg "function renderEntrypoint|const renderEntrypoint|export.*renderEntrypoint" -A 10Repository: ProverCoderAI/docker-git
Length of output: 50380
🏁 Script executed:
# Check package.json for dependencies
cat package.json | head -100Repository: ProverCoderAI/docker-git
Length of output: 4503
🏁 Script executed:
# Look for fast-check imports or usage
rg "from.*fast-check|import.*fc\." --type tsRepository: ProverCoderAI/docker-git
Length of output: 50
🏁 Script executed:
# Find renderCloneBody and git ref generation logic
rg "renderCloneBody|git.*fetch.*refs|refs/heads|refs/tags" -A 3 -B 2Repository: ProverCoderAI/docker-git
Length of output: 17230
🏁 Script executed:
# Check if fast-check is mentioned anywhere in the codebase (even if not installed)
rg "fast-check|fc\." --type ts --max-count 10Repository: ProverCoderAI/docker-git
Length of output: 50
🏁 Script executed:
# Look at the package.json for lib package specifically
cat packages/lib/package.json | head -150Repository: ProverCoderAI/docker-git
Length of output: 3283
Add explicit negative assertions for merge-request and pull-request refs.
The test validates the clone-cache refspec invariant (documented in tasks.ts) but is incomplete. Add expect(entrypoint).not.toContain("'+refs/pull/*:refs/pull/*'") and expect(entrypoint).not.toContain("'+refs/merge-requests/*:refs/merge-requests/*'") to prevent regression if those refs are accidentally reintroduced.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@packages/lib/tests/core/templates.test.ts` around lines 77 - 86, The test for
"renderEntrypoint clone cache" is missing negative assertions for pull-request
and merge-request refspecs; update the spec for the entrypoint returned by
renderEntrypoint(makeTemplateConfig()) to assert it does not contain the
undesired refs by adding checks that entrypoint does not contain
"'+refs/pull/*:refs/pull/*'" and
"'+refs/merge-requests/*:refs/merge-requests/*'". Ensure you add these two
expect(...).not.toContain(...) assertions alongside the existing negative check
so the test prevents regressions.
2 participants
Summary
Final BuildGitHub Actions workflow for Ubuntu, macOS, and Windows that builds both packages, smoke-tests both CLIs, and uploads package tarballs.chmodwith a Bun helper.Reproduction and Verification
packages/app/tests/docker-git/package-scripts-cross-platform.test.tsbefore implementing the script changes.25728183189:E2E (Clone cache)timed out after1800son the second cache reuse case while refreshing broadrefs/*.packages/lib/tests/core/templates.test.tsproving mirror refreshes includerefs/heads/*andrefs/tags/*but not broadrefs/*.Local Checks
bun run --cwd packages/lib test -- tests/core/templates.test.tsbun run --cwd packages/app test -- tests/docker-git/package-scripts-cross-platform.test.tsbun run buildbun run typecheckbun run lintbun run lint:effectbun run check:dist-deps-prunebun run testgit diff --checkMathematical Guarantees
Invariants
forall os in {linux, macos, windows}: final-build(os) -> build(os) and cli_help(app, os) and cli_help(session_sync, os)forall r in clone_cache_refresh_refs: r in refs/heads/* union refs/tags/*forall npm_script in checked_scripts: not contains(npm_script, "bash -lc")Preconditions
Postconditions
refs/pull/*orrefs/merge-requests/*through broadrefs/*.Complexity
O(|all remote refs|)toO(|heads| + |tags|).SOURCE: n/a
Fixes #278