[LCORE-1393] chore: add agents.md and symlinked claude.md#1250
[LCORE-1393] chore: add agents.md and symlinked claude.md#1250tisnik merged 1 commit intolightspeed-core:mainfrom
Conversation
WalkthroughThis PR adds a comprehensive development guide document to the Lightspeed Core Stack project, covering environment setup, architecture, coding standards, testing strategies, dependencies, and development workflows, without introducing functional code changes. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~5 minutes Possibly related PRs
Suggested labels
Suggested reviewers
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 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: 1
🧹 Nitpick comments (1)
AGENTS.md (1)
16-42: Add languages to fenced code blocks (markdownlint MD040).Line 16 and Line 124 use unlabeled fenced blocks; this will keep lint warnings active.
Proposed doc fix
-``` +```text src/ ├── app/ # FastAPI application ... └── constants.py # Shared constants@@
-+text
tests/
├── unit/ # Unit tests (pytest)
├── integration/ # Integration tests (pytest)
└── e2e/ # End-to-end tests (behave)
└── features/ # Gherkin feature filesAlso applies to: 124-130
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@AGENTS.md` around lines 16 - 42, The markdown fenced code blocks in AGENTS.md are unlabeled (the directory listing and the tests block) causing markdownlint MD040 warnings; update each triple-backtick fence (the top directory tree block around the src/ listing and the tests/ block later) to include a language identifier (e.g., text) after the opening ``` so the blocks read ```text and silence the MD040 lint error while preserving formatting.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@AGENTS.md`:
- Around line 11-12: Update the "Linting Tools" section to match the actual
`make verify` target: replace the listed tools so they exactly match the verify
command (black, pylint, pyright, ruff, docstyle, check-types) and remove mypy
from that list (or alternatively split the section into two subsections clearly
labeled "verify tools" and "additional/optional tools" and move mypy into the
optional list); ensure the section text references the `make verify` target and
the same tool names used in the header so readers see an exact correspondence
between `uv run make verify` and the listed tools.
---
Nitpick comments:
In `@AGENTS.md`:
- Around line 16-42: The markdown fenced code blocks in AGENTS.md are unlabeled
(the directory listing and the tests block) causing markdownlint MD040 warnings;
update each triple-backtick fence (the top directory tree block around the src/
listing and the tests/ block later) to include a language identifier (e.g.,
text) after the opening ``` so the blocks read ```text and silence the MD040
lint error while preserving formatting.
| - `uv run make verify` - Run all linters (black, pylint, pyright, ruff, docstyle, check-types) | ||
|
|
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Verify the actual tools behind `make verify` and compare with AGENTS.md claims.
set -euo pipefail
makefile_path="$(fd -HI '^Makefile$' | head -n1 || true)"
if [ -z "${makefile_path}" ]; then
echo "Makefile not found"
exit 0
fi
echo "== Makefile path =="
echo "${makefile_path}"
echo
echo "== verify target (with context) =="
rg -n -A20 -B2 '^[[:alnum:]_.-]*verify[[:space:]]*:' "${makefile_path}"
echo
echo "== AGENTS.md references =="
rg -n -A4 -B2 'make verify|Linting Tools|mypy|pydocstyle|check-types|pyright|pylint|ruff|black' AGENTS.mdRepository: lightspeed-core/lightspeed-stack
Length of output: 1884
Align make verify tool list in the Linting Tools section.
Line 11 correctly lists the verify target tools (black, pylint, pyright, ruff, docstyle, check-types), but the Linting Tools section at lines 173-180 includes tools not part of verify (mypy) and omits check-types. Update lines 173-180 to match what verify actually runs, or clarify which tools are part of verify versus optional/additional type checking tools.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@AGENTS.md` around lines 11 - 12, Update the "Linting Tools" section to match
the actual `make verify` target: replace the listed tools so they exactly match
the verify command (black, pylint, pyright, ruff, docstyle, check-types) and
remove mypy from that list (or alternatively split the section into two
subsections clearly labeled "verify tools" and "additional/optional tools" and
move mypy into the optional list); ensure the section text references the `make
verify` target and the same tool names used in the header so readers see an
exact correspondence between `uv run make verify` and the listed tools.
There was a problem hiding this comment.
This is correct the tool section highlights the tool name itself.. mypy is the tool, check-types is the make target.
There was a problem hiding this comment.
@asamal4, thank you for the clarification! You're absolutely right—I misunderstood the intent. The Linting Tools section correctly lists the actual tool names (mypy, pylint, pyright, ruff, black), while check-types is the make target that invokes mypy. My apologies for the confusion.
✏️ Learnings added
Learnt from: asamal4
Repo: lightspeed-core/lightspeed-stack PR: 1250
File: AGENTS.md:11-12
Timestamp: 2026-03-02T15:57:10.746Z
Learning: In lightspeed-stack's AGENTS.md, the Linting Tools section lists actual tool names (e.g., mypy, pylint, pyright, ruff, black), not make target names. For example, `check-types` is a make target that runs mypy, but mypy is the tool name documented in the Linting Tools section.
Note: Learnings are effective only in the context of similar code segments. To apply general coding guidelines, please configure review instructions. You can manage existing learnings in the app.
🧠 Learnings used
Learnt from: CR
Repo: lightspeed-core/lightspeed-stack PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-02-17T13:52:19.771Z
Learning: Run `uv run make verify` to execute all linters (black, pylint, pyright, ruff, docstyle, check-types) before completion
asamal4
changed the title
2 participants
Description
Standard practice:
Type of change
Tools used to create PR
Identify any AI code assistants used in this PR (for transparency and review context)
Related Tickets & Documents
Checklist before requesting a review
Testing
Summary by CodeRabbit