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/curriculum.yml:
- Around line 81-94: The typescript-syntax job is labeled advisory but will fail
the workflow because the step running node scripts/ts_syntax_check.mjs exits
non-zero on errors; update the typescript-syntax job to be non-blocking by
either (A) replacing the single-step run of node scripts/ts_syntax_check.mjs in
the "syntax-check all .ts files" step with a small wrapper that captures the
JSON output from scripts/ts_syntax_check.mjs, parses it and prints warnings
(mirroring the python-syntax handling), and exits 0, or (B) simpler: set
continue-on-error: true on the "syntax-check all .ts files" step so failures are
advisory; modify the typescript-syntax job/step accordingly.

In @.pre-commit-config.yaml:
- Around line 31-38: The comment "mypy is advisory only — do not block commits"
is misleading because the pre-commit hook with id: mypy currently blocks commits
on failure; either remove that comment or make the hook non-blocking by adding
the advisory option (e.g., add verbose: true or set the hook to not fail) to the
mypy hook configuration; update the block that contains repo:
https://github.com/pre-commit/mirrors-mypy, rev: v1.15.0, hooks -> - id: mypy to
reflect the chosen change.

In `@Makefile`:
- Around line 41-42: The Makefile test target uses "--timeout=60" which
conflicts with pyproject.toml's "timeout = 30"; update the Makefile test target
(the "test:" rule invoking $(PYTHON) -m pytest --timeout=60 -x) to use the same
timeout value as pyproject.toml (30) or, if 60s is intentional, add a brief
comment above the "test:" target explaining why this override is required so
maintainers understand the discrepancy.
- Around line 70-72: The scaffold Makefile target currently only validates SLUG;
add validation for PHASE as well so both required variables are checked before
calling scaffold-lesson.sh: in the scaffold target (symbol: scaffold) ensure you
test -n "$(PHASE)" and test -n "$(SLUG)" and emit the usage message "Usage: make
scaffold PHASE=NN SLUG=lesson-name" and exit non‑zero if either is missing, then
invoke bash scripts/scaffold-lesson.sh $(PHASE) $(SLUG) only when both are
present.

In `@scripts/quiz_coverage.py`:
- Around line 148-152: The printed phase path reconstruction is lossy—stop
rebuilding the slug from c.phase_name; instead preserve and use the original
directory slug in PhaseCoverage. Update the code that builds PhaseCoverage
(e.g., constructor/factory for PhaseCoverage and the function that maps slugs to
names like _phase_slug_to_name) to store the original slug into a field (e.g.,
phase_slug or original_slug), and then change the printing loop (the block
iterating coverages and using c.phase_id and c.phase_name) to use that stored
slug (c.phase_slug) when formatting the output path so the exact original
directory name is emitted.

In `@scripts/scaffold_tests.py`:
- Around line 83-87: In the lines that call lines.append which build the comment
block (the three calls that currently use f-strings but contain no
placeholders), remove the unnecessary leading "f" so they become normal string
literals (keep the final lines.append that uses fname/rel/py_files as an
f-string since it contains placeholders); look for the lines.append(...) calls
that reference rel, fname and py_files to identify the correct statements and
change only the f-prefixed literals that have no interpolation.

---

Nitpick comments:
In `@LESSON_TEMPLATE.md`:
- Around line 165-177: Update the "Code File Guidelines" section to explicitly
require "Include at least 5 unit tests" that are runnable via the Python stdlib
test runner; specifically add a bullet saying lesson code must include 5+ unit
tests in files named test_*.py (or discoverable by python -m unittest) and that
tests should run with the project's runner (scripts/lesson_run.py) and not rely
on external frameworks unless declared in a `# requires:` header. This clarifies
the enforced minimum and how tests must be structured and executed.

In
`@phases/01-math-foundations/01-linear-algebra-intuition/code/tests/test_main.py`:
- Around line 23-26: Update the zip invocation in the test_sub test to use
strict=True to ensure both sequences are the same length; in function test_sub
(which constructs v = vectors.Vector([5, 7, 9]) - vectors.Vector([1, 2, 3]) and
iterates over v.components), change the zip(v.components, [4.0, 5.0, 6.0]) call
to zip(v.components, [4.0, 5.0, 6.0], strict=True) so mismatched lengths raise
an error rather than silently truncating.

In `@scripts/ts_syntax_check.mjs`:
- Around line 90-94: The diagnostics assignment currently wraps
ts.getParseDiagnostics(sf) in [].concat() unnecessarily; update the diagnostics
variable to directly use the array returned by ts.getParseDiagnostics(sf)
(replace the [].concat(ts.getParseDiagnostics(sf)) expression with
ts.getParseDiagnostics(sf)) so the code reads const diagnostics =
ts.getParseDiagnostics(sf); and remove the redundant concat wrapper.

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 @.pre-commit-config.yaml:
- Line 38: The comment in .pre-commit-config.yaml incorrectly states "mypy
checks scripts/ with permissive rules"; update that comment to say scripts/ uses
stricter/strict mypy rules per pyproject.toml (see the [[tool.mypy.overrides]]
for scripts.* and the disallow_untyped_defs = true override) so the comment
accurately reflects that scripts/ is checked with stricter settings rather than
permissive ones.

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
`@phases/01-math-foundations/01-linear-algebra-intuition/code/tests/test_linear_algebra.py`:
- Line 25: Confirm that using zip(..., strict=True) in test_linear_algebra.py is
safe by ensuring the project's Python requirement covers it (check
requires-python in pyproject.toml is >=3.10) and CI runs a Python >=3.8 (CI uses
3.12); if the project did not guarantee that, replace the expression in the test
that iterates v.components (the zip call with strict=True) with a compatible
alternative (e.g., explicit length check plus plain zip) so tests run on older
interpreters.