code-review-ai-cli 1.0.2__tar.gz → 1.2.0__tar.gz

{code_review_ai_cli-1.0.2 → code_review_ai_cli-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-review-ai-cli
-Version: 1.0.2
+Version: 1.2.0
 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
@@ -47,7 +47,9 @@ Automated code review tool with Pull Request integration for Azure DevOps/TFS an
 - **Dry-run Mode** — Validate reviews before posting
 - **Multiple LLM Providers** — OpenAI, Azure OpenAI, Gemini, Claude, Ollama, GitHub Copilot, AWS Bedrock
 - **Smart Filtering** — Filter by file extensions, limit diff size
-- **Customizable Prompts** — Markdown-based review guidelines
+- **Project-aware PR Context** — Sends repository and linked work item context while restricting findings to modified PR lines
+- **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
 
 ## Installation & Quick Start
@@ -87,7 +89,9 @@ ai-review init
 
 Creates:
 - `config.yaml` — LLM and review settings
-- `review_prompt.md` — Customizable review guidelines
+- `review_context.example.md` — Canonical example reviewer context
+- `review_context.local.md` — Local reviewer context override, ignored by git
+- `.gitignore` entry for `review_context.local.md`
 
 ### 3. Run Your First Review
 
@@ -100,6 +104,9 @@ ai-review pr-review 42
 
 # Dry-run (preview without posting)
 ai-review pr-review 42 --dry-run
+
+# Check stored token/cost usage
+ai-review usage
 ```
 
 ## Configuration File
@@ -122,10 +129,45 @@ tfs:
 review:
   language: pt
   verbosity: detailed                  # or: quick, security
+  scope: diff_with_context             # diff_with_context, diff_only, full_code
   file_extensions_filter: [".cs", ".ts", ".py"]
   max_diff_files: 50
+  max_comments_to_post: 20
+  custom_prompt_file: review_context.local.md
+  project_context:
+    enabled: true
+    mode: on_demand                      # on_demand, full
+    manifest_max_chars: 60000
+    retrieval_max_rounds: 2
+    retrieval_max_files: 20
+    retrieval_max_chars: 120000
+    retrieval_file_max_chars: 30000
+  work_item_context:
+    enabled: true
+    max_items: 20
 ```
 
+By default, repository context is loaded on demand: the prompt includes explicit
+source-branch change packets, full changed-file contents as read-only context,
+linked work item documentation, and a repository manifest, then the model
+requests any extra files it needs. Inline PR comments must still be grounded in
+actual changed lines from the change packets. Set
+`review.project_context.mode: full` to send the full eligible repository
+snapshot instead. Bedrock uses a default estimated prompt budget of 180000
+tokens; override it with `llm.max_prompt_tokens` if your model supports more or
+less.
+
+Reviewer context is loaded from exactly one Markdown file. By default the CLI
+uses `review_context.local.md` when it exists, otherwise it falls back to the
+packaged `src/prompts/review_context.example.md`. Keep local team tweaks in
+`review_context.local.md`; it is gitignored so the canonical context cannot
+drift across machines.
+
+For Copilot-backed reviews, Claude Sonnet models are often strong choices for
+large PR validation, for example `llm.provider: copilot` with a Claude Sonnet
+model available to your organization. The tool still enforces the same
+source-branch grounding, duplicate checks, and comment cap regardless of model.
+
 ## Development & Testing
 
 This is a standard Python project with the following structure:

{code_review_ai_cli-1.0.2 → code_review_ai_cli-1.2.0}/README.md

@@ -10,7 +10,9 @@ Automated code review tool with Pull Request integration for Azure DevOps/TFS an
 - **Dry-run Mode** — Validate reviews before posting
 - **Multiple LLM Providers** — OpenAI, Azure OpenAI, Gemini, Claude, Ollama, GitHub Copilot, AWS Bedrock
 - **Smart Filtering** — Filter by file extensions, limit diff size
-- **Customizable Prompts** — Markdown-based review guidelines
+- **Project-aware PR Context** — Sends repository and linked work item context while restricting findings to modified PR lines
+- **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
 
 ## Installation & Quick Start
@@ -50,7 +52,9 @@ ai-review init
 
 Creates:
 - `config.yaml` — LLM and review settings
-- `review_prompt.md` — Customizable review guidelines
+- `review_context.example.md` — Canonical example reviewer context
+- `review_context.local.md` — Local reviewer context override, ignored by git
+- `.gitignore` entry for `review_context.local.md`
 
 ### 3. Run Your First Review
 
@@ -63,6 +67,9 @@ ai-review pr-review 42
 
 # Dry-run (preview without posting)
 ai-review pr-review 42 --dry-run
+
+# Check stored token/cost usage
+ai-review usage
 ```
 
 ## Configuration File
@@ -85,10 +92,45 @@ tfs:
 review:
   language: pt
   verbosity: detailed                  # or: quick, security
+  scope: diff_with_context             # diff_with_context, diff_only, full_code
   file_extensions_filter: [".cs", ".ts", ".py"]
   max_diff_files: 50
+  max_comments_to_post: 20
+  custom_prompt_file: review_context.local.md
+  project_context:
+    enabled: true
+    mode: on_demand                      # on_demand, full
+    manifest_max_chars: 60000
+    retrieval_max_rounds: 2
+    retrieval_max_files: 20
+    retrieval_max_chars: 120000
+    retrieval_file_max_chars: 30000
+  work_item_context:
+    enabled: true
+    max_items: 20
 ```
 
+By default, repository context is loaded on demand: the prompt includes explicit
+source-branch change packets, full changed-file contents as read-only context,
+linked work item documentation, and a repository manifest, then the model
+requests any extra files it needs. Inline PR comments must still be grounded in
+actual changed lines from the change packets. Set
+`review.project_context.mode: full` to send the full eligible repository
+snapshot instead. Bedrock uses a default estimated prompt budget of 180000
+tokens; override it with `llm.max_prompt_tokens` if your model supports more or
+less.
+
+Reviewer context is loaded from exactly one Markdown file. By default the CLI
+uses `review_context.local.md` when it exists, otherwise it falls back to the
+packaged `src/prompts/review_context.example.md`. Keep local team tweaks in
+`review_context.local.md`; it is gitignored so the canonical context cannot
+drift across machines.
+
+For Copilot-backed reviews, Claude Sonnet models are often strong choices for
+large PR validation, for example `llm.provider: copilot` with a Claude Sonnet
+model available to your organization. The tool still enforces the same
+source-branch grounding, duplicate checks, and comment cap regardless of model.
+
 ## Development & Testing
 
 This is a standard Python project with the following structure:
@@ -155,4 +197,4 @@ Predefined tasks for quick execution in VS Code:
 In VS Code:
 1. `Ctrl+Shift+P` → "Tasks: Run Task"
 2. Select the desired task
-3. Fill in parameters if needed
+3. Fill in parameters if needed

{code_review_ai_cli-1.0.2 → code_review_ai_cli-1.2.0}/code_review_ai_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-review-ai-cli
-Version: 1.0.2
+Version: 1.2.0
 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
@@ -47,7 +47,9 @@ Automated code review tool with Pull Request integration for Azure DevOps/TFS an
 - **Dry-run Mode** — Validate reviews before posting
 - **Multiple LLM Providers** — OpenAI, Azure OpenAI, Gemini, Claude, Ollama, GitHub Copilot, AWS Bedrock
 - **Smart Filtering** — Filter by file extensions, limit diff size
-- **Customizable Prompts** — Markdown-based review guidelines
+- **Project-aware PR Context** — Sends repository and linked work item context while restricting findings to modified PR lines
+- **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
 
 ## Installation & Quick Start
@@ -87,7 +89,9 @@ ai-review init
 
 Creates:
 - `config.yaml` — LLM and review settings
-- `review_prompt.md` — Customizable review guidelines
+- `review_context.example.md` — Canonical example reviewer context
+- `review_context.local.md` — Local reviewer context override, ignored by git
+- `.gitignore` entry for `review_context.local.md`
 
 ### 3. Run Your First Review
 
@@ -100,6 +104,9 @@ ai-review pr-review 42
 
 # Dry-run (preview without posting)
 ai-review pr-review 42 --dry-run
+
+# Check stored token/cost usage
+ai-review usage
 ```
 
 ## Configuration File
@@ -122,10 +129,45 @@ tfs:
 review:
   language: pt
   verbosity: detailed                  # or: quick, security
+  scope: diff_with_context             # diff_with_context, diff_only, full_code
   file_extensions_filter: [".cs", ".ts", ".py"]
   max_diff_files: 50
+  max_comments_to_post: 20
+  custom_prompt_file: review_context.local.md
+  project_context:
+    enabled: true
+    mode: on_demand                      # on_demand, full
+    manifest_max_chars: 60000
+    retrieval_max_rounds: 2
+    retrieval_max_files: 20
+    retrieval_max_chars: 120000
+    retrieval_file_max_chars: 30000
+  work_item_context:
+    enabled: true
+    max_items: 20
 ```
 
+By default, repository context is loaded on demand: the prompt includes explicit
+source-branch change packets, full changed-file contents as read-only context,
+linked work item documentation, and a repository manifest, then the model
+requests any extra files it needs. Inline PR comments must still be grounded in
+actual changed lines from the change packets. Set
+`review.project_context.mode: full` to send the full eligible repository
+snapshot instead. Bedrock uses a default estimated prompt budget of 180000
+tokens; override it with `llm.max_prompt_tokens` if your model supports more or
+less.
+
+Reviewer context is loaded from exactly one Markdown file. By default the CLI
+uses `review_context.local.md` when it exists, otherwise it falls back to the
+packaged `src/prompts/review_context.example.md`. Keep local team tweaks in
+`review_context.local.md`; it is gitignored so the canonical context cannot
+drift across machines.
+
+For Copilot-backed reviews, Claude Sonnet models are often strong choices for
+large PR validation, for example `llm.provider: copilot` with a Claude Sonnet
+model available to your organization. The tool still enforces the same
+source-branch grounding, duplicate checks, and comment cap regardless of model.
+
 ## Development & Testing
 
 This is a standard Python project with the following structure:

{code_review_ai_cli-1.0.2 → code_review_ai_cli-1.2.0}/code_review_ai_cli.egg-info/SOURCES.txt

@@ -13,11 +13,13 @@ src/formatter.py
 src/git_utils.py
 src/llm_client.py
 src/tfs_client.py
+src/usage_tracker.py
 src/prompts/config.yaml.template
-src/prompts/review_prompt.md.template
+src/prompts/review_context.example.md
 tests/test_ai_review.py
 tests/test_config.py
 tests/test_formatter.py
 tests/test_git_utils.py
 tests/test_llm_client.py
-tests/test_tfs_client.py
+tests/test_tfs_client.py
+tests/test_usage_tracker.py

{code_review_ai_cli-1.0.2 → code_review_ai_cli-1.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "code-review-ai-cli"
-version = "1.0.2"
+version = "1.2.0"
 description = "Automated AI-powered code review CLI for Azure DevOps / TFS Pull Requests"
 readme = "README.md"
 requires-python = ">=3.10"