code-review-ai-cli 1.2.0__tar.gz → 1.3.0__tar.gz

{code_review_ai_cli-1.2.0 → code_review_ai_cli-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-review-ai-cli
-Version: 1.2.0
+Version: 1.3.0
 Summary: Automated AI-powered code review CLI for Azure DevOps / TFS Pull Requests
 License: MIT
 Keywords: code-review,ai,azure-devops,tfs,pull-request,llm
@@ -48,10 +48,48 @@ Automated code review tool with Pull Request integration for Azure DevOps/TFS an
 - **Multiple LLM Providers** — OpenAI, Azure OpenAI, Gemini, Claude, Ollama, GitHub Copilot, AWS Bedrock
 - **Smart Filtering** — Filter by file extensions, limit diff size
 - **Project-aware PR Context** — Sends repository and linked work item context while restricting findings to modified PR lines
+- **RAG Context** — Enriches the review with related code snippets found via `git grep` in the local repository
 - **Single Reviewer Context** — One Markdown context file with local override support
 - **Usage Tracking** — Store per-PR token usage and optional cost estimates
 - **Interactive CLI** — Menu-driven selection and confirmation
 
+## Local Repository Requirement
+
+> **The CLI must be run from inside the local clone of the repository being reviewed.**
+
+The PR diff is fetched from Azure DevOps/TFS, but several features depend on the local git state:
+
+| Feature | Local dependency |
+|---|---|
+| PR diff | `git fetch` + three-dot diff against `origin/<branch>` |
+| RAG context | `git grep` on the working tree |
+| Branch validation | `git branch --show-current` |
+
+### Branch requirement when RAG is enabled
+
+When `review.rag.enabled: true`, the local repository **must be checked out on the PR target branch** (e.g. `development`). If the local branch differs from the target, the review is blocked:
+
+```
+Local branch mismatch: you are on 'main' but this PR targets 'development'.
+RAG context would be built from the wrong branch, which may corrupt the review.
+Please run:  git checkout development
+```
+
+**Example:**
+```bash
+# PR: merge 'feature/my-feature' → 'development'
+cd /path/to/my-repo          # must be inside the repo
+git checkout development     # must match PR target branch
+ai-review pr-review 42
+```
+
+To skip the branch check entirely, disable RAG:
+```yaml
+review:
+  rag:
+    enabled: false
+```
+
 ## Installation & Quick Start
 
 ### 1. Install Package
@@ -129,11 +167,14 @@ tfs:
 review:
   language: pt
   verbosity: detailed                  # or: quick, security
-  scope: diff_with_context             # diff_with_context, diff_only, full_code
+  scope: diff_with_context             # diff_with_context, diff_only
   file_extensions_filter: [".cs", ".ts", ".py"]
   max_diff_files: 50
   max_comments_to_post: 20
   custom_prompt_file: review_context.local.md
+  rag:
+    enabled: true                      # requires local branch == PR target
+    max_chars: 40000
   project_context:
     enabled: true
     mode: on_demand                      # on_demand, full
@@ -180,11 +221,59 @@ src/
   tfs_client.py       # Azure DevOps integration
   git_utils.py        # Git diff processing
   formatter.py        # Output formatting (terminal, markdown, JSON)
+  rag_engine.py       # RAG context via git grep
 
 tests/
   test_*.py           # Unit and integration tests
 ```
 
+## RAG Context
+
+### Current Implementation
+
+The RAG engine enriches the LLM prompt with related code snippets found in the local repository:
+
+1. **Extract identifiers** — function and class names are parsed from the PR diff
+2. **Search** — `git grep` finds files containing those identifiers
+3. **Extract snippets** — ±10 lines around each match are included as read-only context
+
+All operations run locally with no extra dependencies. The quality of RAG context depends entirely on the local repository state, which is why the **local branch must match the PR target branch**.
+
+### Recommended Stack for Enhanced RAG (Local & Open Source)
+
+For teams wanting semantic similarity instead of keyword search, the recommended local stack is:
+
+| Component | Library | Reason |
+|---|---|---|
+| **Vector database** | [ChromaDB](https://www.trychroma.com/) | Runs in-memory or persists to a local SQLite file — no server needed, `pip install chromadb` |
+| **Embeddings** | [sentence-transformers](https://www.sbert.net/) | Generates vectors locally on CPU — no API calls, no cost |
+
+Example integration pattern:
+
+```python
+from sentence_transformers import SentenceTransformer
+import chromadb
+
+model = SentenceTransformer("all-MiniLM-L6-v2")   # ~80 MB, CPU-friendly
+client = chromadb.Client()                          # in-memory
+collection = client.create_collection("repo-index")
+
+# Index
+collection.add(
+    documents=[snippet_text],
+    embeddings=model.encode([snippet_text]).tolist(),
+    ids=["file:line"],
+)
+
+# Query
+results = collection.query(
+    query_embeddings=model.encode([query]).tolist(),
+    n_results=5,
+)
+```
+
+This stack keeps the CLI lightweight (`pip install`) and requires no external services or paid APIs.
+
 ### Run Tests
 
 ```bash

{code_review_ai_cli-1.2.0 → code_review_ai_cli-1.3.0}/README.md

@@ -11,10 +11,48 @@ Automated code review tool with Pull Request integration for Azure DevOps/TFS an
 - **Multiple LLM Providers** — OpenAI, Azure OpenAI, Gemini, Claude, Ollama, GitHub Copilot, AWS Bedrock
 - **Smart Filtering** — Filter by file extensions, limit diff size
 - **Project-aware PR Context** — Sends repository and linked work item context while restricting findings to modified PR lines
+- **RAG Context** — Enriches the review with related code snippets found via `git grep` in the local repository
 - **Single Reviewer Context** — One Markdown context file with local override support
 - **Usage Tracking** — Store per-PR token usage and optional cost estimates
 - **Interactive CLI** — Menu-driven selection and confirmation
 
+## Local Repository Requirement
+
+> **The CLI must be run from inside the local clone of the repository being reviewed.**
+
+The PR diff is fetched from Azure DevOps/TFS, but several features depend on the local git state:
+
+| Feature | Local dependency |
+|---|---|
+| PR diff | `git fetch` + three-dot diff against `origin/<branch>` |
+| RAG context | `git grep` on the working tree |
+| Branch validation | `git branch --show-current` |
+
+### Branch requirement when RAG is enabled
+
+When `review.rag.enabled: true`, the local repository **must be checked out on the PR target branch** (e.g. `development`). If the local branch differs from the target, the review is blocked:
+
+```
+Local branch mismatch: you are on 'main' but this PR targets 'development'.
+RAG context would be built from the wrong branch, which may corrupt the review.
+Please run:  git checkout development
+```
+
+**Example:**
+```bash
+# PR: merge 'feature/my-feature' → 'development'
+cd /path/to/my-repo          # must be inside the repo
+git checkout development     # must match PR target branch
+ai-review pr-review 42
+```
+
+To skip the branch check entirely, disable RAG:
+```yaml
+review:
+  rag:
+    enabled: false
+```
+
 ## Installation & Quick Start
 
 ### 1. Install Package
@@ -92,11 +130,14 @@ tfs:
 review:
   language: pt
   verbosity: detailed                  # or: quick, security
-  scope: diff_with_context             # diff_with_context, diff_only, full_code
+  scope: diff_with_context             # diff_with_context, diff_only
   file_extensions_filter: [".cs", ".ts", ".py"]
   max_diff_files: 50
   max_comments_to_post: 20
   custom_prompt_file: review_context.local.md
+  rag:
+    enabled: true                      # requires local branch == PR target
+    max_chars: 40000
   project_context:
     enabled: true
     mode: on_demand                      # on_demand, full
@@ -143,11 +184,59 @@ src/
   tfs_client.py       # Azure DevOps integration
   git_utils.py        # Git diff processing
   formatter.py        # Output formatting (terminal, markdown, JSON)
+  rag_engine.py       # RAG context via git grep
 
 tests/
   test_*.py           # Unit and integration tests
 ```
 
+## RAG Context
+
+### Current Implementation
+
+The RAG engine enriches the LLM prompt with related code snippets found in the local repository:
+
+1. **Extract identifiers** — function and class names are parsed from the PR diff
+2. **Search** — `git grep` finds files containing those identifiers
+3. **Extract snippets** — ±10 lines around each match are included as read-only context
+
+All operations run locally with no extra dependencies. The quality of RAG context depends entirely on the local repository state, which is why the **local branch must match the PR target branch**.
+
+### Recommended Stack for Enhanced RAG (Local & Open Source)
+
+For teams wanting semantic similarity instead of keyword search, the recommended local stack is:
+
+| Component | Library | Reason |
+|---|---|---|
+| **Vector database** | [ChromaDB](https://www.trychroma.com/) | Runs in-memory or persists to a local SQLite file — no server needed, `pip install chromadb` |
+| **Embeddings** | [sentence-transformers](https://www.sbert.net/) | Generates vectors locally on CPU — no API calls, no cost |
+
+Example integration pattern:
+
+```python
+from sentence_transformers import SentenceTransformer
+import chromadb
+
+model = SentenceTransformer("all-MiniLM-L6-v2")   # ~80 MB, CPU-friendly
+client = chromadb.Client()                          # in-memory
+collection = client.create_collection("repo-index")
+
+# Index
+collection.add(
+    documents=[snippet_text],
+    embeddings=model.encode([snippet_text]).tolist(),
+    ids=["file:line"],
+)
+
+# Query
+results = collection.query(
+    query_embeddings=model.encode([query]).tolist(),
+    n_results=5,
+)
+```
+
+This stack keeps the CLI lightweight (`pip install`) and requires no external services or paid APIs.
+
 ### Run Tests
 
 ```bash

{code_review_ai_cli-1.2.0 → code_review_ai_cli-1.3.0}/code_review_ai_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-review-ai-cli
-Version: 1.2.0
+Version: 1.3.0
 Summary: Automated AI-powered code review CLI for Azure DevOps / TFS Pull Requests
 License: MIT
 Keywords: code-review,ai,azure-devops,tfs,pull-request,llm
@@ -48,10 +48,48 @@ Automated code review tool with Pull Request integration for Azure DevOps/TFS an
 - **Multiple LLM Providers** — OpenAI, Azure OpenAI, Gemini, Claude, Ollama, GitHub Copilot, AWS Bedrock
 - **Smart Filtering** — Filter by file extensions, limit diff size
 - **Project-aware PR Context** — Sends repository and linked work item context while restricting findings to modified PR lines
+- **RAG Context** — Enriches the review with related code snippets found via `git grep` in the local repository
 - **Single Reviewer Context** — One Markdown context file with local override support
 - **Usage Tracking** — Store per-PR token usage and optional cost estimates
 - **Interactive CLI** — Menu-driven selection and confirmation
 
+## Local Repository Requirement
+
+> **The CLI must be run from inside the local clone of the repository being reviewed.**
+
+The PR diff is fetched from Azure DevOps/TFS, but several features depend on the local git state:
+
+| Feature | Local dependency |
+|---|---|
+| PR diff | `git fetch` + three-dot diff against `origin/<branch>` |
+| RAG context | `git grep` on the working tree |
+| Branch validation | `git branch --show-current` |
+
+### Branch requirement when RAG is enabled
+
+When `review.rag.enabled: true`, the local repository **must be checked out on the PR target branch** (e.g. `development`). If the local branch differs from the target, the review is blocked:
+
+```
+Local branch mismatch: you are on 'main' but this PR targets 'development'.
+RAG context would be built from the wrong branch, which may corrupt the review.
+Please run:  git checkout development
+```
+
+**Example:**
+```bash
+# PR: merge 'feature/my-feature' → 'development'
+cd /path/to/my-repo          # must be inside the repo
+git checkout development     # must match PR target branch
+ai-review pr-review 42
+```
+
+To skip the branch check entirely, disable RAG:
+```yaml
+review:
+  rag:
+    enabled: false
+```
+
 ## Installation & Quick Start
 
 ### 1. Install Package
@@ -129,11 +167,14 @@ tfs:
 review:
   language: pt
   verbosity: detailed                  # or: quick, security
-  scope: diff_with_context             # diff_with_context, diff_only, full_code
+  scope: diff_with_context             # diff_with_context, diff_only
   file_extensions_filter: [".cs", ".ts", ".py"]
   max_diff_files: 50
   max_comments_to_post: 20
   custom_prompt_file: review_context.local.md
+  rag:
+    enabled: true                      # requires local branch == PR target
+    max_chars: 40000
   project_context:
     enabled: true
     mode: on_demand                      # on_demand, full
@@ -180,11 +221,59 @@ src/
   tfs_client.py       # Azure DevOps integration
   git_utils.py        # Git diff processing
   formatter.py        # Output formatting (terminal, markdown, JSON)
+  rag_engine.py       # RAG context via git grep
 
 tests/
   test_*.py           # Unit and integration tests
 ```
 
+## RAG Context
+
+### Current Implementation
+
+The RAG engine enriches the LLM prompt with related code snippets found in the local repository:
+
+1. **Extract identifiers** — function and class names are parsed from the PR diff
+2. **Search** — `git grep` finds files containing those identifiers
+3. **Extract snippets** — ±10 lines around each match are included as read-only context
+
+All operations run locally with no extra dependencies. The quality of RAG context depends entirely on the local repository state, which is why the **local branch must match the PR target branch**.
+
+### Recommended Stack for Enhanced RAG (Local & Open Source)
+
+For teams wanting semantic similarity instead of keyword search, the recommended local stack is:
+
+| Component | Library | Reason |
+|---|---|---|
+| **Vector database** | [ChromaDB](https://www.trychroma.com/) | Runs in-memory or persists to a local SQLite file — no server needed, `pip install chromadb` |
+| **Embeddings** | [sentence-transformers](https://www.sbert.net/) | Generates vectors locally on CPU — no API calls, no cost |
+
+Example integration pattern:
+
+```python
+from sentence_transformers import SentenceTransformer
+import chromadb
+
+model = SentenceTransformer("all-MiniLM-L6-v2")   # ~80 MB, CPU-friendly
+client = chromadb.Client()                          # in-memory
+collection = client.create_collection("repo-index")
+
+# Index
+collection.add(
+    documents=[snippet_text],
+    embeddings=model.encode([snippet_text]).tolist(),
+    ids=["file:line"],
+)
+
+# Query
+results = collection.query(
+    query_embeddings=model.encode([query]).tolist(),
+    n_results=5,
+)
+```
+
+This stack keeps the CLI lightweight (`pip install`) and requires no external services or paid APIs.
+
 ### Run Tests
 
 ```bash

{code_review_ai_cli-1.2.0 → code_review_ai_cli-1.3.0}/code_review_ai_cli.egg-info/SOURCES.txt

@@ -12,6 +12,7 @@ src/config.py
 src/formatter.py
 src/git_utils.py
 src/llm_client.py
+src/rag_engine.py
 src/tfs_client.py
 src/usage_tracker.py
 src/prompts/config.yaml.template
@@ -21,5 +22,6 @@ tests/test_config.py
 tests/test_formatter.py
 tests/test_git_utils.py
 tests/test_llm_client.py
+tests/test_rag_engine.py
 tests/test_tfs_client.py
 tests/test_usage_tracker.py

{code_review_ai_cli-1.2.0 → code_review_ai_cli-1.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "code-review-ai-cli"
-version = "1.2.0"
+version = "1.3.0"
 description = "Automated AI-powered code review CLI for Azure DevOps / TFS Pull Requests"
 readme = "README.md"
 requires-python = ">=3.10"

{code_review_ai_cli-1.2.0 → code_review_ai_cli-1.3.0}/src/ai_review.py

@@ -84,6 +84,7 @@ from src.config import ReviewConfig, VALID_PROVIDERS
 from src.git_utils import GitUtils, GitError
 from src.llm_client import LLMClient, LLMError
 from src.formatter import ReviewFormatter, Colors, save_output
+from src.rag_engine import obter_contexto_rag
 from src.usage_tracker import (
     append_usage_record,
     build_pr_usage_record,
@@ -94,7 +95,7 @@ from src.usage_tracker import (
 from src import __version__ as VERSION
 
 
-REVIEW_SCOPE_CHOICES = ["diff_only", "diff_with_context", "full_code"]
+REVIEW_SCOPE_CHOICES = ["diff_only", "diff_with_context"]
 
 
 def _get_spinner_frames() -> list[str]:
@@ -263,7 +264,7 @@ def _add_global_options(parser: argparse.ArgumentParser) -> None:
         "--review-scope", default=None,
         choices=REVIEW_SCOPE_CHOICES,
         help=(
-            "Review scope: diff_with_context (default), diff_only, or full_code"
+            "Review scope: diff_with_context (default) or diff_only"
         )
     )
     group_review.add_argument(
@@ -333,11 +334,6 @@ def _review_scope_context_note(review_scope: str) -> str:
             "Context will be used for understanding only; review comments remain "
             "limited to modified PR lines."
         )
-    if scope == "full_code":
-        return (
-            "Review is running in full_code mode; full changed files are context, "
-            "but comments remain limited to actual PR changes."
-        )
     return "Review is running in diff_only mode."
 
 
@@ -786,7 +782,6 @@ def _comment_mentions_non_anchor_terms(comment: dict, anchor_text: str) -> bool:
         comment.get("comment", ""),
         comment.get("anchor_code", ""),
         comment.get("problematic_code", ""),
-        comment.get("evidence", ""),
     ):
         if term not in anchor_text:
             return True
@@ -904,15 +899,15 @@ def _filter_comments_to_grounded_source_lines(
             discarded_grounding.append(comment)
             continue
 
-        if not _text_contains_evidence(anchor_text, anchor_code):
+        if not evidence:
             discarded_grounding.append(comment)
             continue
 
-        if not _text_contains_evidence(anchor_text, problematic_code):
+        if not _text_contains_evidence(anchor_text, anchor_code):
             discarded_grounding.append(comment)
             continue
 
-        if not _text_contains_evidence(anchor_text, evidence):
+        if not _text_contains_evidence(anchor_text, problematic_code):
             discarded_grounding.append(comment)
             continue
 
@@ -924,10 +919,6 @@ def _filter_comments_to_grounded_source_lines(
             discarded_grounding.append(comment)
             continue
 
-        if not _text_contains_evidence(source_text, evidence):
-            discarded_grounding.append(comment)
-            continue
-
         if _comment_mentions_absent_source_terms(comment, source_text):
             discarded_grounding.append(comment)
             continue
@@ -1381,19 +1372,29 @@ def run_pr_review_workflow(args: argparse.Namespace, config: ReviewConfig,
     # Show PR details
     print(formatter.format_pr_details(pr_details))
 
-    # --- Get PR diff ---
+    # --- Get PR diff via git local ---
     print(formatter.format_progress("Getting Pull Request diff"))
 
+    _local_repo = (config.tfs_local_repo_path or "").strip() or os.getcwd()
+    git_utils_pr = GitUtils(repo_path=_local_repo, pat=config.tfs_pat)
+
     try:
-        diff = tfs.get_pull_request_diff(
-            repo_name,
-            pr_id,
-            review_scope=config.review_scope,
-        )
+        target_ref, source_ref = tfs.obter_dados_pr(pr_id)
     except TFSError as exc:
         print(formatter.format_error(str(exc)))
         return 1
 
+    try:
+        git_utils_pr.fetch_merge_commit(source_ref)
+    except GitError as exc:
+        print(formatter.format_warning(f"Could not fetch source branch: {exc}"))
+
+    try:
+        diff = git_utils_pr.get_pr_diff(target_ref, source_ref)
+    except GitError as exc:
+        print(formatter.format_error(str(exc)))
+        return 1
+
     if not diff.strip():
         print(formatter.format_warning("PR contains no code changes."))
         return 0
@@ -1411,8 +1412,13 @@ def run_pr_review_workflow(args: argparse.Namespace, config: ReviewConfig,
         print(formatter.format_info("🔍 DRY-RUN mode: comments will NOT be posted"))
 
     # Get diff files summary
-    git_utils = GitUtils.__new__(GitUtils)
-    git_utils.repo_path = os.getcwd()
+    git_utils = git_utils_pr
+
+    # --- Noise filter (binary, lock files, oversized sections) ---
+    diff = git_utils_pr.filter_diff_noise(diff, config.max_diff_lines)
+    if not diff.strip():
+        print(formatter.format_warning("After filtering noise (binary/lock files), the diff is empty."))
+        return 0
 
     # Filter extensions before limiting/truncating the diff sent to the LLM
     if config.file_extensions_filter:
@@ -1460,7 +1466,41 @@ def run_pr_review_workflow(args: argparse.Namespace, config: ReviewConfig,
         ))
 
     use_contextual_review = review_scope == "diff_with_context"
-    load_changed_file_context = review_scope in ("diff_with_context", "full_code")
+    load_changed_file_context = review_scope == "diff_with_context"
+
+    # --- RAG context ---
+    rag_context = ""
+    if config.rag_enabled and diff_truncated.strip():
+        # Verify local branch matches the PR target branch to avoid RAG context contamination.
+        _target_branch = target_ref.removeprefix("origin/")
+        try:
+            _local_branch = git_utils_pr.get_current_branch()
+        except GitError as exc:
+            print(formatter.format_error(
+                f"Cannot determine local branch: {exc}\n"
+                "Ensure the local repository is accessible and try again."
+            ))
+            return 1
+
+        if _local_branch != _target_branch:
+            print(formatter.format_error(
+                f"Local branch mismatch: you are on '{_local_branch}' "
+                f"but this PR targets '{_target_branch}'.\n"
+                f"RAG context would be built from the wrong branch, which may corrupt the review.\n"
+                f"Please run:  git checkout {_target_branch}"
+            ))
+            return 1
+
+        print(formatter.format_progress("Loading RAG context from local repository"))
+        rag_context = obter_contexto_rag(
+            diff_truncated,
+            repo_path=git_utils.repo_path,
+            max_chars=config.rag_max_chars,
+        )
+        if rag_context:
+            print(formatter.format_info(
+                f"RAG context loaded ({len(rag_context):,} characters)."
+            ))
 
     work_item_context = ""
     linked_work_item_ids: list[int] | None = None
@@ -1604,7 +1644,7 @@ def run_pr_review_workflow(args: argparse.Namespace, config: ReviewConfig,
         structured_comments = llm.review_pr_structured(
             diff=diff_truncated,
             files_summary=files_summary,
-            context=getattr(args, "context", ""),
+            context="\n\n".join(filter(None, [getattr(args, "context", ""), rag_context])),
             review_scope=config.review_scope,
             project_context=project_context,
             work_item_context=work_item_context,

{code_review_ai_cli-1.2.0 → code_review_ai_cli-1.3.0}/src/config.py

@@ -84,11 +84,12 @@ class ReviewConfig:
     tfs_verify_ssl: bool = True              # Verify TLS certificates
     tfs_ca_bundle: str = ""                 # Path to corporate CA bundle (.pem)
     tfs_repository: str = ""                # Default repository (empty = all)
+    tfs_local_repo_path: str = ""           # Local clone path of the reviewed repo (empty = cwd)
 
     # --- Review -------------------------------------------------------
     review_language: str = "pt"             # Review language (pt/en)
     verbosity: str = "detailed"             # "quick" | "detailed" | "security"
-    review_scope: str = "diff_with_context"  # "diff_only" | "diff_with_context" | "full_code"
+    review_scope: str = "diff_with_context"  # "diff_only" | "diff_with_context"
     max_diff_files: int = 50                 # Max diff files sent to LLM
     max_diff_lines: int = 2000              # Max diff lines
     max_comments_to_post: int = 20          # Max actionable inline comments per review
@@ -141,6 +142,10 @@ class ReviewConfig:
         "Microsoft.VSTS.TCM.SystemInfo",
     ])
 
+    # --- RAG Context --------------------------------------------------
+    rag_enabled: bool = True                 # Enable RAG context retrieval
+    rag_max_chars: int = 40000               # Max characters for RAG context
+
     # --- PR Review ----------------------------------------------------
     auto_post_comments: bool = False        # Post comments automatically
     dry_run: bool = False                   # Review without posting
@@ -260,6 +265,7 @@ class ReviewConfig:
             "tfs_verify_ssl": ("tfs", "verify_ssl"),
             "tfs_ca_bundle": ("tfs", "ca_bundle"),
             "tfs_repository": ("tfs", "repository"),
+            "tfs_local_repo_path": ("tfs", "local_repo_path"),
             # Review
             "review_language": ("review", "language"),
             "verbosity": ("review", "verbosity"),
@@ -284,6 +290,8 @@ class ReviewConfig:
             "work_item_context_max_items": ("review", "work_item_context", "max_items"),
             "work_item_context_max_chars": ("review", "work_item_context", "max_chars"),
             "work_item_context_fields": ("review", "work_item_context", "fields"),
+            "rag_enabled": ("review", "rag", "enabled"),
+            "rag_max_chars": ("review", "rag", "max_chars"),
             # PR
             "auto_post_comments": ("pr", "auto_post_comments"),
             "dry_run": ("pr", "dry_run"),
@@ -377,10 +385,10 @@ class ReviewConfig:
                 "Use 'quick', 'detailed' or 'security'."
             )
 
-        if self.review_scope not in ("diff_only", "diff_with_context", "full_code"):
+        if self.review_scope not in ("diff_only", "diff_with_context"):
             issues.append(
                 f"Invalid review scope: '{self.review_scope}'. "
-                "Use 'diff_only', 'diff_with_context' or 'full_code'."
+                "Use 'diff_only' or 'diff_with_context'."
             )
 
         if self.max_diff_files <= 0: