LCORE-1841: Demo deck: LCORE weak points for AI-driven agentic flow#1586
Conversation
|
Warning Rate limit exceeded
Your organization is not enrolled in usage-based pricing. Contact your admin to enable usage-based pricing to continue reviews beyond the rate limit, or try again in 49 minutes and 53 seconds. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (1)
WalkthroughCI/CD workflows and Makefile were updated to narrow linting scope from the entire repository to only the Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
✨ Simplify code
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 |
tisnik
changed the title
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 7
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.github/workflows/pydocstyle.yaml:
- Line 20: The CI pydocstyle invocation checks both src and tests but the
Makefile docstyle target only checks src, causing local `make verify` to miss
test docstring issues; update the Makefile target named "docstyle" so its
pydocstyle invocation matches the workflow (run pydocstyle -v src tests) —
locate the docstyle target in the Makefile and add "tests" to the paths checked
(or unify both CI and Makefile to use the same path list).
In @.github/workflows/ruff.yaml:
- Line 20: Remove the redundant per-file-ignores flag from the ruff invocation:
the command "uv tool run ruff check src tests --per-file-ignores=tests/*:S101
--per-file-ignores=scripts/*:S101" should be simplified to omit
"--per-file-ignores=scripts/*:S101" since ruff is only checking "src" and
"tests"; keep the tests ignore only.
In `@docs/demos/lcore/weak_points_for_ai.html`:
- Line 2: Add a lang attribute to the root HTML element (the <html> tag) to
provide a language hint for screen readers and validators; update the <html> tag
in docs/demos/lcore/weak_points_for_ai.html (the root <html> element) to include
an appropriate language code (for example lang="en" or the correct locale for
the document) and ensure any related tooling or templates that generate this
file also propagate that attribute.
In `@docs/demos/lcore/weak_points_for_ai.md`:
- Around line 17-21: Fix three small text issues in the slide content: change
"It allow developers" to "It allows developers" in the first bullet, change
"LLMS" to "LLMs" in the "Context-awareness problem" bullet (to match deck
usage), and on the separate slide replace "An interesting are to research" with
"An interesting area to research"; update those exact phrases in the markdown so
rendering and consistency are corrected.
- Around line 264-306: Remove the stray closing parenthesis after the loop in
the _filter_tools_for_response snippet (the lone ')' following
result.append(tool)) which causes a syntax error; delete that extraneous
character so the function returns result properly and ensure indentation of the
return result line remains aligned with the if filtered_tool_names: block.
In `@docs/demos/lcore/weak_points_for_ai/ex5.py`:
- Around line 144-148: The snippet has a stray closing parenthesis after
result.append(tool) causing a SyntaxError; remove the extraneous ')' so the loop
appends correctly (look for the result.append(tool) statement inside the
function that builds and returns result) and ensure the function returns result
or [] as intended.
In `@Makefile`:
- Line 102: Makefile targets use inconsistent lint scopes and the verify target
is missing linters; update the black, ruff, docstyle, and format targets to use
the same scope as CI (src tests) instead of . or only src, and modify or add the
verify target so it invokes all linters (black, ruff, docstyle, pylint, pyright)
— reference the Makefile targets named format, black, ruff, docstyle, and verify
to locate and change their commands so local checks match CI and include the
missing linters.
🪄 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: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: 8311f70d-efe2-4f57-ac81-a731d177f0a9
📒 Files selected for processing (15)
.github/workflows/black.yaml.github/workflows/pydocstyle.yaml.github/workflows/ruff.yamlMakefiledocs/README.mddocs/demos/lcore/weak_points_for_ai.htmldocs/demos/lcore/weak_points_for_ai.mddocs/demos/lcore/weak_points_for_ai/ex1.pydocs/demos/lcore/weak_points_for_ai/ex2.pydocs/demos/lcore/weak_points_for_ai/ex3.pydocs/demos/lcore/weak_points_for_ai/ex4.pydocs/demos/lcore/weak_points_for_ai/ex5.pydocs/demos/lcore/weak_points_for_ai/ex6.pydocs/demos/lcore/weak_points_for_ai/ex7.pydocs/index.md
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (16)
- GitHub Check: bandit
- GitHub Check: pydocstyle
- GitHub Check: Pyright
- GitHub Check: radon
- GitHub Check: unit_tests (3.13)
- GitHub Check: build-pr
- GitHub Check: Pylinter
- GitHub Check: unit_tests (3.12)
- GitHub Check: Konflux kflux-prd-rh02 / lightspeed-stack-on-pull-request
- GitHub Check: E2E: server mode / ci / group 3
- GitHub Check: E2E: library mode / ci / group 2
- GitHub Check: E2E: library mode / ci / group 1
- GitHub Check: E2E: server mode / ci / group 1
- GitHub Check: E2E: server mode / ci / group 2
- GitHub Check: E2E: library mode / ci / group 3
- GitHub Check: E2E Tests for Lightspeed Evaluation job
🧰 Additional context used
📓 Path-based instructions (1)
**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
**/*.py: Use absolute imports for internal modules:from authentication import get_auth_dependency
Import FastAPI dependencies with:from fastapi import APIRouter, HTTPException, Request, status, Depends
Import Llama Stack client with:from llama_stack_client import AsyncLlamaStackClient
Checkconstants.pyfor shared constants before defining new ones
All modules start with descriptive docstrings explaining purpose
Uselogger = get_logger(__name__)fromlog.pyfor module logging
Type aliases defined at module level for clarity
Use Final[type] as type hint for all constants
All functions require docstrings with brief descriptions
Complete type annotations for parameters and return types in functions
Usetyping_extensions.Selffor model validators in Pydantic models
Use modern union type syntaxstr | intinstead ofUnion[str, int]
UseOptional[Type]for optional type hints
Use snake_case with descriptive, action-oriented function names (get_, validate_, check_)
Avoid in-place parameter modification anti-patterns; return new data structures instead
Useasync deffor I/O operations and external API calls
HandleAPIConnectionErrorfrom Llama Stack in error handling
Use standard log levels with clear purposes: debug, info, warning, error
All classes require descriptive docstrings explaining purpose
Use PascalCase for class names with standard suffixes: Configuration, Error/Exception, Resolver, Interface
Use ABC for abstract base classes with@abstractmethoddecorators
Use@model_validatorand@field_validatorfor Pydantic model validation
Complete type annotations for all class attributes; use specific types, notAny
Follow Google Python docstring conventions with Parameters, Returns, Raises, and Attributes sections
Files:
docs/demos/lcore/weak_points_for_ai/ex4.pydocs/demos/lcore/weak_points_for_ai/ex3.pydocs/demos/lcore/weak_points_for_ai/ex2.pydocs/demos/lcore/weak_points_for_ai/ex6.pydocs/demos/lcore/weak_points_for_ai/ex1.pydocs/demos/lcore/weak_points_for_ai/ex7.pydocs/demos/lcore/weak_points_for_ai/ex5.py
🧠 Learnings (4)
📚 Learning: 2026-04-19T15:40:25.624Z
Learnt from: CR
Repo: lightspeed-core/lightspeed-stack PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-04-19T15:40:25.624Z
Learning: Use `uv run make verify` to run all linters (black, pylint, pyright, ruff, docstyle, check-types)
Applied to files:
.github/workflows/pydocstyle.yaml.github/workflows/black.yaml.github/workflows/ruff.yamlMakefile
📚 Learning: 2026-04-19T15:40:25.624Z
Learnt from: CR
Repo: lightspeed-core/lightspeed-stack PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-04-19T15:40:25.624Z
Learning: Use `uv run make format` to auto-format code with black + ruff
Applied to files:
.github/workflows/black.yaml.github/workflows/ruff.yamlMakefile
📚 Learning: 2026-04-16T19:08:38.217Z
Learnt from: Lifto
Repo: lightspeed-core/lightspeed-stack PR: 1524
File: src/app/endpoints/responses.py:523-529
Timestamp: 2026-04-16T19:08:38.217Z
Learning: In lightspeed-stack (`src/app/endpoints/responses.py`), the predicate `server_label in configured_mcp_labels` is the established, intentional pattern for identifying server-deployed MCP tools across `_sanitize_response_dict`, `_is_server_mcp_output_item`, and `_should_filter_mcp_chunk`. Client-supplied tools cannot collide with configured server labels because `server_label` is a server-side field set by lightspeed-stack during tool injection; clients send `function` tools or MCP tools pointing at their own servers with different labels. Do not flag this predicate as a false-positive collision risk in code review.
Applied to files:
docs/demos/lcore/weak_points_for_ai/ex5.py
📚 Learning: 2026-02-25T07:46:39.608Z
Learnt from: asimurka
Repo: lightspeed-core/lightspeed-stack PR: 1211
File: src/models/responses.py:8-16
Timestamp: 2026-02-25T07:46:39.608Z
Learning: In the lightspeed-stack codebase, src/models/requests.py uses OpenAIResponseInputTool as Tool while src/models/responses.py uses OpenAIResponseTool as Tool. This type difference is intentional - input tools and output/response tools have different schemas in llama-stack-api.
Applied to files:
docs/demos/lcore/weak_points_for_ai/ex5.py
🪛 HTMLHint (1.9.2)
docs/demos/lcore/weak_points_for_ai.html
[warning] 2-2: An lang attribute must be present on elements.
(html-lang-require)
🪛 LanguageTool
docs/demos/lcore/weak_points_for_ai.md
[grammar] ~30-~30: Ensure spelling is correct
Context: ...red to other Python-based apps) * A bit complection was already "achieved" --- ## Weak po...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
[grammar] ~37-~37: Ensure spelling is correct
Context: ...oints in LCORE * Consistency * Risk of complection * Risk of having too many ad-hoc data t...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
[style] ~46-~46: ‘Overall structure’ might be wordy. Consider a shorter alternative.
Context: ...or LLMs) - just few places --- ## Overall structure * Stateful REST API * Without global m...
(EN_WORDINESS_PREMIUM_OVERALL_STRUCTURE)
[style] ~58-~58: To form a complete sentence, be sure to include a subject.
Context: ... --- ## Static vs dynamic structure * Might be critical for LLMs to understand the ...
(MISSING_IT_THERE)
[grammar] ~350-~350: Use a hyphen to join words.
Context: ... description stored in AGENTS.md * Low level consistency - syntax level ...
(QB_NEW_EN_HYPHEN)
[style] ~355-~355: To elevate your writing, try using a synonym here.
Context: ...sistency - architecture level - hard to check and maintain --- ## Python f...
(HARD_TO)
🔇 Additional comments (3)
docs/demos/lcore/weak_points_for_ai/ex6.py (1)
1-12: LGTM — illustrative anti-pattern is clearly framed.The leading comments make it explicit that the magic-number usage is the weak point being demonstrated, so this serves the demo deck as intended.
docs/demos/lcore/weak_points_for_ai.html (1)
7-23: Reveal.js assets are properly vendored and reachable.All referenced CSS and JS files exist in the repository at the correct relative paths (
dist/reset.css,dist/reveal.css,dist/theme/simple.css,plugin/highlight/github.css,dist/reveal.js,plugin/notes/notes.js,plugin/markdown/markdown.js,plugin/highlight/highlight.js). The file follows the same asset structure as all other existing demo HTMLs indocs/demos/lcore/and will render correctly without silent failure.> Likely an incorrect or invalid review comment..github/workflows/black.yaml (1)
20-20: CI and Makefile black targets are now consistentThe change correctly aligns the CI workflow with the updated Makefile
blacktarget (line 102). Both now checksrc tests.Note: The
formattarget in the Makefile (line 58) still usesblack ., which was already flagged in the Makefile review.
| python-version: '3.12' | ||
| - name: Python linter | ||
| run: uv tool run pydocstyle -v . | ||
| run: uv tool run pydocstyle -v src tests |
There was a problem hiding this comment.
Inconsistency with Makefile docstyle target
This CI workflow now checks src tests, but the Makefile docstyle target (line 111) only checks src. Developers running make verify locally will not catch docstring issues in tests/.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.github/workflows/pydocstyle.yaml at line 20, The CI pydocstyle invocation
checks both src and tests but the Makefile docstyle target only checks src,
causing local `make verify` to miss test docstring issues; update the Makefile
target named "docstyle" so its pydocstyle invocation matches the workflow (run
pydocstyle -v src tests) — locate the docstyle target in the Makefile and add
"tests" to the paths checked (or unify both CI and Makefile to use the same path
list).
| python-version: '3.12' | ||
| - name: Python linter | ||
| run: uv tool run ruff check . --per-file-ignores=tests/*:S101 --per-file-ignores=scripts/*:S101 | ||
| run: uv tool run ruff check src tests --per-file-ignores=tests/*:S101 --per-file-ignores=scripts/*:S101 |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Redundant ignore pattern for scripts/*
The --per-file-ignores=scripts/*:S101 flag has no effect since the checked scope is now src tests and does not include the scripts directory.
♻️ Cleanup redundant flag
- run: uv tool run ruff check src tests --per-file-ignores=tests/*:S101 --per-file-ignores=scripts/*:S101
+ run: uv tool run ruff check src tests --per-file-ignores=tests/*:S101📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| run: uv tool run ruff check src tests --per-file-ignores=tests/*:S101 --per-file-ignores=scripts/*:S101 | |
| run: uv tool run ruff check src tests --per-file-ignores=tests/*:S101 |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.github/workflows/ruff.yaml at line 20, Remove the redundant
per-file-ignores flag from the ruff invocation: the command "uv tool run ruff
check src tests --per-file-ignores=tests/*:S101
--per-file-ignores=scripts/*:S101" should be simplified to omit
"--per-file-ignores=scripts/*:S101" since ruff is only checking "src" and
"tests"; keep the tests ignore only.
| @@ -0,0 +1,36 @@ | |||
| <!doctype html> | |||
| <html> | |||
There was a problem hiding this comment.
Add lang attribute on <html> for accessibility.
Screen readers and validators expect a language hint on the root element.
♻️ Proposed fix
-<html>
+<html lang="en">📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| <html> | |
| <html lang="en"> |
🧰 Tools
🪛 HTMLHint (1.9.2)
[warning] 2-2: An lang attribute must be present on elements.
(html-lang-require)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@docs/demos/lcore/weak_points_for_ai.html` at line 2, Add a lang attribute to
the root HTML element (the <html> tag) to provide a language hint for screen
readers and validators; update the <html> tag in
docs/demos/lcore/weak_points_for_ai.html (the root <html> element) to include an
appropriate language code (for example lang="en" or the correct locale for the
document) and ensure any related tooling or templates that generate this file
also propagate that attribute.
| if filtered_tool_names: | ||
| result = [] | ||
| for tool in tools: | ||
| tool_dict = tool if isinstance(tool, dict) else tool.model_dump() | ||
| tool_type = tool_dict.get("type") | ||
|
|
||
| if tool_type == "mcp" and len(filtered_tool_names) > 0: | ||
| # Get the endpoint for this MCP config | ||
| mcp_endpoint = tool_dict.get("server_url", "") | ||
| server_label = tool_dict.get("server_label", "unknown") | ||
|
|
||
| # Filter to only include tools that belong to this endpoint | ||
| endpoint_tools = [ | ||
| tool_name | ||
| for tool_name in filtered_tool_names | ||
| if tool_to_endpoint.get(tool_name) == mcp_endpoint | ||
| ] | ||
|
|
||
| if endpoint_tools: | ||
| if isinstance(tool, dict): | ||
| tool["allowed_tools"] = endpoint_tools | ||
| else: | ||
| tool.allowed_tools = endpoint_tools | ||
| result.append(tool) | ||
| else: | ||
| logger.warning( | ||
| "MCP server %s (%s) has no matching tools - skipping from result", | ||
| server_label, | ||
| mcp_endpoint, | ||
| ) | ||
| else: | ||
| # Non-MCP tools (file_search, function) are always included | ||
| logger.debug( | ||
| "Including non-MCP tool: type=%s, config=%s", | ||
| tool_type, | ||
| tool_dict.get("name") if tool_type == "function" else tool_type, | ||
| ) | ||
| result.append(tool) | ||
|
|
||
| ) | ||
| return result | ||
| return [] | ||
| ``` |
There was a problem hiding this comment.
Stray ) in displayed Python snippet — invalid syntax on the slide.
Inside the _filter_tools_for_response snippet, the loop body ends at result.append(tool) (line 301), then there is a lone ) on line 303 before return result. This is a copy-paste artifact and will render as a syntax error on the slide (and break syntax highlighting around that point).
♻️ Proposed fix
logger.debug(
"Including non-MCP tool: type=%s, config=%s",
tool_type,
tool_dict.get("name") if tool_type == "function" else tool_type,
)
result.append(tool)
- )
return result
return []📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| if filtered_tool_names: | |
| result = [] | |
| for tool in tools: | |
| tool_dict = tool if isinstance(tool, dict) else tool.model_dump() | |
| tool_type = tool_dict.get("type") | |
| if tool_type == "mcp" and len(filtered_tool_names) > 0: | |
| # Get the endpoint for this MCP config | |
| mcp_endpoint = tool_dict.get("server_url", "") | |
| server_label = tool_dict.get("server_label", "unknown") | |
| # Filter to only include tools that belong to this endpoint | |
| endpoint_tools = [ | |
| tool_name | |
| for tool_name in filtered_tool_names | |
| if tool_to_endpoint.get(tool_name) == mcp_endpoint | |
| ] | |
| if endpoint_tools: | |
| if isinstance(tool, dict): | |
| tool["allowed_tools"] = endpoint_tools | |
| else: | |
| tool.allowed_tools = endpoint_tools | |
| result.append(tool) | |
| else: | |
| logger.warning( | |
| "MCP server %s (%s) has no matching tools - skipping from result", | |
| server_label, | |
| mcp_endpoint, | |
| ) | |
| else: | |
| # Non-MCP tools (file_search, function) are always included | |
| logger.debug( | |
| "Including non-MCP tool: type=%s, config=%s", | |
| tool_type, | |
| tool_dict.get("name") if tool_type == "function" else tool_type, | |
| ) | |
| result.append(tool) | |
| ) | |
| return result | |
| return [] | |
| ``` | |
| if filtered_tool_names: | |
| result = [] | |
| for tool in tools: | |
| tool_dict = tool if isinstance(tool, dict) else tool.model_dump() | |
| tool_type = tool_dict.get("type") | |
| if tool_type == "mcp" and len(filtered_tool_names) > 0: | |
| # Get the endpoint for this MCP config | |
| mcp_endpoint = tool_dict.get("server_url", "") | |
| server_label = tool_dict.get("server_label", "unknown") | |
| # Filter to only include tools that belong to this endpoint | |
| endpoint_tools = [ | |
| tool_name | |
| for tool_name in filtered_tool_names | |
| if tool_to_endpoint.get(tool_name) == mcp_endpoint | |
| ] | |
| if endpoint_tools: | |
| if isinstance(tool, dict): | |
| tool["allowed_tools"] = endpoint_tools | |
| else: | |
| tool.allowed_tools = endpoint_tools | |
| result.append(tool) | |
| else: | |
| logger.warning( | |
| "MCP server %s (%s) has no matching tools - skipping from result", | |
| server_label, | |
| mcp_endpoint, | |
| ) | |
| else: | |
| # Non-MCP tools (file_search, function) are always included | |
| logger.debug( | |
| "Including non-MCP tool: type=%s, config=%s", | |
| tool_type, | |
| tool_dict.get("name") if tool_type == "function" else tool_type, | |
| ) | |
| result.append(tool) | |
| return result | |
| return [] |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@docs/demos/lcore/weak_points_for_ai.md` around lines 264 - 306, Remove the
stray closing parenthesis after the loop in the _filter_tools_for_response
snippet (the lone ')' following result.append(tool)) which causes a syntax
error; delete that extraneous character so the function returns result properly
and ensure indentation of the return result line remains aligned with the if
filtered_tool_names: block.
| result.append(tool) | ||
|
|
||
| ) | ||
| return result | ||
| return [] |
There was a problem hiding this comment.
Stray ) on line 146 — syntax error in the demo snippet.
Line 146 contains a lone ) that does not close any opening delimiter in the surrounding scope. As written, this snippet won't parse as valid Python and will likely confuse readers of the slide deck. It looks like a leftover from a removed comprehension/call wrapper.
🛠 Proposed fix
result.append(tool)
- )
return result
return []🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@docs/demos/lcore/weak_points_for_ai/ex5.py` around lines 144 - 148, The
snippet has a stray closing parenthesis after result.append(tool) causing a
SyntaxError; remove the extraneous ')' so the loop appends correctly (look for
the result.append(tool) statement inside the function that builds and returns
result) and ensure the function returns result or [] as intended.
|
|
||
| black: ## Check source code using Black code formatter | ||
| uv run black --check . | ||
| uv run black --check src tests |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Description: Extract all linting/formatting commands to verify scope consistency
echo "=== Makefile linting targets ==="
rg -A1 '^(black|ruff|pylint|pyright|docstyle|format):' Makefile
echo -e "\n=== CI workflow linting commands ==="
rg 'run:.*\b(black|ruff|pydocstyle)' .github/workflows/Repository: lightspeed-core/lightspeed-stack
Length of output: 1005
🏁 Script executed:
cat -n Makefile | grep -A 5 "^[[:space:]]*format:"Repository: lightspeed-core/lightspeed-stack
Length of output: 58
🏁 Script executed:
cat -n Makefile | grep -A 10 "^[[:space:]]*verify:"Repository: lightspeed-core/lightspeed-stack
Length of output: 58
🏁 Script executed:
# Get more context around the targets
rg -B1 -A 3 '(format|verify|ruff|docstyle):' MakefileRepository: lightspeed-core/lightspeed-stack
Length of output: 469
Fix inconsistent linting scope across Makefile targets and add missing linters to verify target
The black target uses src tests but several related targets remain inconsistent:
- format target (lines 58–59): both
blackandruffstill use.instead ofsrc tests - ruff target (line 114): uses
.instead ofsrc tests(CI usessrc tests) - docstyle target (line 111): uses only
srcinstead ofsrc tests(CI usessrc tests) - verify target (missing): does not run
ruffordocstyleat all, despite the learning noting it should run all linters (black, pylint, pyright, ruff, docstyle)
The scope inconsistency between Makefile and CI workflows, combined with the incomplete verify target, causes local verification to not match CI and misses linting checks.
Suggested fixes for consistency
format: ## Format the code into unified format
- uv run black .
- uv run ruff check . --fix
+ uv run black src tests
+ uv run ruff check src tests --fix --per-file-ignores=tests/*:S101 --per-file-ignores=scripts/*:S101 ruff: ## Check source code using Ruff linter
- uv run ruff check . --per-file-ignores=tests/*:S101 --per-file-ignores=scripts/*:S101
+ uv run ruff check src tests --per-file-ignores=tests/*:S101 --per-file-ignores=scripts/*:S101 docstyle: ## Check the docstring style using Docstyle checker
- uv run pydocstyle -v src
+ uv run pydocstyle -v src tests verify: ## Run all linters
$(MAKE) black
$(MAKE) pylint
$(MAKE) pyright
+ $(MAKE) ruff
+ $(MAKE) docstyle🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@Makefile` at line 102, Makefile targets use inconsistent lint scopes and the
verify target is missing linters; update the black, ruff, docstyle, and format
targets to use the same scope as CI (src tests) instead of . or only src, and
modify or add the verify target so it invokes all linters (black, ruff,
docstyle, pylint, pyright) — reference the Makefile targets named format, black,
ruff, docstyle, and verify to locate and change their commands so local checks
match CI and include the missing linters.
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
1 participant
Description
LCORE-1841: Demo deck: LCORE weak points for AI-driven agentic flow
Type of change
Tools used to create PR
Related Tickets & Documents
Summary by CodeRabbit
Documentation
Chores