refactor main.py and separate concerns - #96
Merged
Conversation
📝 WalkthroughWalkthroughThe change extracts LLM configuration, schemas, prompts, provider helpers, and FastAPI routes from ChangesLLM API refactor
Estimated code review effort: 4 (Complex) | ~45 minutes Sequence Diagram(s)sequenceDiagram
participant Client
participant Router
participant LLM
participant Provider
Client->>Router: POST /api/ai/parse
Router->>LLM: Normalize provider and create completion
LLM->>Provider: Send prompt with JSON response settings
Provider-->>LLM: Return model content
LLM-->>Router: Parse JSON content
Router-->>Client: Return GenerateResponse
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 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 (2)
gen-ai/llm.py (1)
20-30: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueSort
__all__to satisfy Ruff RUF022.Ruff flags
__all__as unsorted. Apply isort-style alphabetical ordering.♻️ Proposed fix
__all__ = [ - "OpenAI", - "OpenAIError", - "NO_LLM_NOTE", - "CANNED_INGREDIENTS", - "get_client", - "openai_available", - "normalize_provider", - "create_chat_completion", - "parse_json_content", + "CANNED_INGREDIENTS", + "NO_LLM_NOTE", + "OpenAI", + "OpenAIError", + "create_chat_completion", + "get_client", + "normalize_provider", + "openai_available", + "parse_json_content", ]🤖 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 `@gen-ai/llm.py` around lines 20 - 30, Sort the symbols in the module-level __all__ list alphabetically in isort/Ruff RUF022 order, preserving all existing exports.Source: Linters/SAST tools
gen-ai/routers.py (1)
45-46: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winAdd structured logging on fallback paths.
Errors are silently swallowed and replaced with fallback data. Without logging, production debugging is difficult since the client always receives a 200.
♻️ Suggested addition for both fallback blocks
import logging + +logger = logging.getLogger(__name__)In each except block:
except (OpenAIError, KeyError, TypeError, ValueError): + logger.exception("LLM call failed, returning fallback response") return GenerateResponse(dish=request.dish, ingredients=CANNED_INGREDIENTS, note=NO_LLM_NOTE)Also applies to: 69-72
🤖 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 `@gen-ai/routers.py` around lines 45 - 46, Add structured logging to both fallback exception handlers in the relevant router endpoint, including the caught exception and useful request context before returning the canned GenerateResponse; preserve the existing fallback response behavior while ensuring both the handler around lines 45-46 and the additional block around lines 69-72 emit logs.
🤖 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 `@gen-ai/routers.py`:
- Line 3: Replace HTTPException with TypeError in both exception clauses within
the relevant router functions, including the handlers around
normalize_provider/build_system_prompt and
create_chat_completion/parse_json_content/Ingredient construction, and remove
the now-unused HTTPException import from fastapi.
---
Nitpick comments:
In `@gen-ai/llm.py`:
- Around line 20-30: Sort the symbols in the module-level __all__ list
alphabetically in isort/Ruff RUF022 order, preserving all existing exports.
In `@gen-ai/routers.py`:
- Around line 45-46: Add structured logging to both fallback exception handlers
in the relevant router endpoint, including the caught exception and useful
request context before returning the canned GenerateResponse; preserve the
existing fallback response behavior while ensuring both the handler around lines
45-46 and the additional block around lines 69-72 emit logs.
🪄 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: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: b98d8881-3824-4805-ba5a-5b0b0997291f
📒 Files selected for processing (13)
gen-ai/config.pygen-ai/llm.pygen-ai/main.pygen-ai/prompts.pygen-ai/pytest.inigen-ai/routers.pygen-ai/schemas.pygen-ai/tests/conftest.pygen-ai/tests/test_endpoint_merge.pygen-ai/tests/test_endpoint_parse.pygen-ai/tests/test_parse_json_content.pygen-ai/tests/test_prompts.pygen-ai/tests/test_provider.py
| @@ -0,0 +1,74 @@ | |||
| import json | |||
|
|
|||
| from fastapi import APIRouter, HTTPException | |||
There was a problem hiding this comment.
🩺 Stability & Availability | 🟡 Minor | ⚡ Quick win
HTTPException is caught but never raised; TypeError is missing from the except clause.
None of the functions called in the try blocks (normalize_provider, build_system_prompt, create_chat_completion, parse_json_content, Ingredient(**item)) raise HTTPException. Conversely, if the LLM returns a non-dict structure (e.g., a top-level JSON array or {"ingredients": [1, 2, 3]}), data["ingredients"] or Ingredient(**item) will raise TypeError, which is not caught and will produce a 500 instead of falling back.
🛡️ Proposed fix: replace HTTPException with TypeError and remove unused import
-from fastapi import APIRouter, HTTPException
+from fastapi import APIRouterApply to both except clauses (lines 45 and 69):
- except (HTTPException, OpenAIError, KeyError, ValueError):
+ except (OpenAIError, KeyError, TypeError, ValueError):Also applies to: 45-45, 69-69
🤖 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 `@gen-ai/routers.py` at line 3, Replace HTTPException with TypeError in both
exception clauses within the relevant router functions, including the handlers
around normalize_provider/build_system_prompt and
create_chat_completion/parse_json_content/Ingredient construction, and remove
the now-unused HTTPException import from fastapi.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #89
gen-ai/main.pyhad grown into a single 312-line file mixing five unrelated concerns. This splits it into focused, single-responsibility modules with a clean acyclic dependency graph, no behavior or HTTP contract changes.main.pyconfig.pyload_dotenv(),Providertypeschemas.pyprompts.pyDIETARY_RULES,build_system_promptllm.pyrouters.pyAPIRouterfor/health,/api/ai/parse,/api/ai/mergeSummary by CodeRabbit
New Features
Bug Fixes
Tests