One flaky test (test_builtin_echo_tool timeout) was stopping the entire
e2e coverage suite via -x, preventing 118+ remaining tests from running
and generating coverage data.
Tests are independent (each gets a fresh browser context via the
function-scoped page fixture), so removing -x is safe.
Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
Add comprehensive documentation at the top of the coverage workflow file
to help developers understand:
- What the coverage workflow does
- How to view coverage reports (Codecov links)
- What coverage files are generated
- Configuration options and requirements
This improves developer experience by making the CI/CD pipeline more
transparent and easier to understand for contributors.
Co-authored-by: enihsago <[email protected]>
* fix(ci): fix three coverage workflow failures
1. Migration ordering: glob `V*.sql` sorted V10 before V1 (ASCII '0' < '_').
Use `sort -V` for correct numeric ordering.
2. Missing WASM channels: telegram_auth_integration tests need the Telegram
WASM binary. Add wasm32-wasip2 target, cargo-component, and
build-wasm-extensions.sh to both coverage and e2e-coverage jobs
(matching test.yml).
3. E2E shell quoting: `cargo llvm-cov show-env` outputs shell-quoted values
(KEY='value') but GITHUB_ENV expects unquoted KEY=value. Strip single
quotes with sed before appending.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix(ci): address PR review feedback on coverage workflow
- Migration loop: use readarray + printf | sort -V instead of $(ls)
to avoid word-splitting on filenames
- cargo-component install: check if already installed first, don't
mask failures with || true
- show-env quote stripping: use targeted regex to strip only wrapping
quotes (KEY='value' -> KEY=value) instead of removing all quotes
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: skip telegram_auth_integration tests when WASM module not built
Replace panicking assert! with a require_telegram_wasm!() macro that
gracefully skips tests when the Telegram WASM binary hasn't been compiled.
This ensures the test suite passes across all configurations (with and
without wasm32-wasip2 target), while still running the tests in CI where
the WASM channels are built.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: panic in CI when telegram WASM module missing, skip locally
- require_telegram_wasm!() now checks the CI env var: panics in CI
(so a broken WASM build step fails loudly) but skips locally
- fs::read error now includes the file path for better diagnostics
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix(ci): persist all cargo-llvm-cov env vars for E2E coverage
Newer cargo-llvm-cov versions output CARGO_ENCODED_RUSTFLAGS instead of
RUSTFLAGS from show-env. The workflow was cherry-picking specific vars
(RUSTFLAGS, LLVM_PROFILE_FILE, etc.) to persist to $GITHUB_ENV, so
CARGO_ENCODED_RUSTFLAGS was never set during the build step, producing a
non-instrumented binary and zero .profraw files.
Replace the manual echo lines with `cargo llvm-cov show-env >> $GITHUB_ENV`
to forward all vars (including CARGO_ENCODED_RUSTFLAGS, CARGO_INCREMENTAL,
etc.) regardless of cargo-llvm-cov version.
Also forward CARGO_ENCODED_RUSTFLAGS in the E2E conftest subprocess env.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix(ci): address PR review — prefix-based env forwarding, split clean step
- conftest.py: replace explicit env var list with prefix-based matching
(CARGO_LLVM_COV*, LLVM_*) plus specific vars (CARGO_ENCODED_RUSTFLAGS,
CARGO_INCREMENTAL) to stay resilient to cargo-llvm-cov changes.
- coverage.yml: move `cargo llvm-cov clean` to its own step so the env
vars from show-env (persisted via $GITHUB_ENV) are active when clean runs.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
The ironclaw binary only handles SIGINT (via tokio::signal::ctrl_c),
not SIGTERM. When conftest.py sent SIGTERM during teardown, the OS
killed the process immediately without running atexit handlers, so
LLVM never flushed .profraw files. cargo llvm-cov report then found
zero profraw files and failed.
- Send SIGINT instead of SIGTERM so the existing ctrl_c handler
triggers graceful shutdown → main() returns → atexit runs → profraw
flushed
- Increase shutdown wait from 5s to 10s for graceful cleanup
- Add a diagnostic step to verify profraw files exist before the
report step, making future issues visible in CI logs
Co-authored-by: Claude Opus 4.6 <[email protected]>
* ci: enhance coverage workflow with feature matrix, postgres, and E2E
Replace single-config coverage job with a multi-job pipeline:
- Mirror test.yml's 3-config feature matrix (all-features, default, libsql-only)
- Add PostgreSQL service (pgvector/pgvector:pg16) with migrations for
postgres configs so integration tests actually run instead of skipping
- Add E2E coverage job using cargo-llvm-cov instrumented binary with
Playwright browser tests
- Add coverage-gate roll-up job for branch protection
- Upload per-config flags to Codecov (all-features, default, libsql-only, e2e)
- Forward LLVM coverage env vars in E2E conftest.py so profraw data
lands where cargo-llvm-cov report expects it
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address PR review feedback on coverage workflow
- Avoid setting DATABASE_URL to empty string for libsql-only config;
use $GITHUB_ENV conditional step so the var is unset entirely
- Add set -euo pipefail and psql -v ON_ERROR_STOP=1 to migrations
so SQL errors fail the job immediately
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* ci: add code coverage with cargo-llvm-cov and Codecov
Add a Coverage workflow that runs on PRs and pushes to main using
cargo-llvm-cov with --all-features, uploading LCOV results to Codecov.
Include codecov.yml config with project/patch targets and ignore rules
for stub files.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* ci: switch Codecov upload to OIDC (tokenless)
Use GitHub OIDC tokens instead of CODECOV_TOKEN secret so coverage
uploads work for fork PRs where secrets are not available.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* ci: fail coverage upload strictly on push, leniently on PRs
Use a conditional so pushes to main fail if Codecov upload breaks
(preventing silent reporting gaps) while PRs stay lenient to avoid
blocking fork PRs where OIDC may not be available.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* ci: disable Codecov auto-detection to suppress warnings
We provide lcov.info explicitly, so disable auto-search for gcov,
coverage.py, and Xcode formats that produce noisy warnings.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* ci: include channels-src and tools-src in coverage reporting
These WASM source directories should be tracked for test coverage
rather than ignored.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* ci: remove stale ignore entries from codecov.yml
The marketplace, ecommerce, taskrabbit, and restaurant stub files
no longer exist in the codebase.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* ci: run coverage on push to main only
Avoids running tests twice on PRs (once in test.yml, once for coverage).
Coverage runs on merge to main instead. Simplify fail_ci_if_error to
always true since it only runs on push now.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
OutBack Dingo