overkill 0.4.0__tar.gz → 0.5.0__tar.gz

{overkill-0.4.0 → overkill-0.5.0}/.github/workflows/test.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.12", "3.13"]
+        python-version: ["3.11", "3.12", "3.13"]
 
     steps:
       - uses: actions/checkout@v6

{overkill-0.4.0 → overkill-0.5.0}/AGENTS.md

@@ -9,7 +9,7 @@
 
 ## Pull Request Rules
 
-Every PR must pass the review loop (`review-loop.sh --dry-run`) before merging. No exceptions. We eat our own dog food — if Mr. Overkill can't approve it, neither can you.
+Every PR must pass the review loop (`overkill review-loop --dry-run`) before merging. No exceptions. We eat our own dog food — if Mr. Overkill can't approve it, neither can you.
 
 ## Branch Rules
 

{overkill-0.4.0 → overkill-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: overkill
-Version: 0.4.0
+Version: 0.5.0
 Summary: AI-powered code review loop — automates Codex review + Claude fix cycles
 Project-URL: Repository, https://github.com/modocai/mr-overkill
 Project-URL: Issues, https://github.com/modocai/mr-overkill/issues
@@ -14,10 +14,11 @@ Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Software Development :: Quality Assurance
-Requires-Python: >=3.12
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 
 # :tophat: Mr. Overkill
@@ -72,7 +73,7 @@ You need these to participate in the madness:
 
 **Runtime**:
 
-- [Python](https://www.python.org/) 3.12+ — for the `overkill` CLI
+- [Python](https://www.python.org/) 3.11+ — for the `overkill` CLI
 - [Node.js](https://nodejs.org/) v18+ — Codex and Claude Code CLI are npm packages, so yes, you need this
 - A fast credit card — essential
 
@@ -392,12 +393,7 @@ uv run mypy src/
 ## Testing
 
 ```bash
-# Python tests
 uv run pytest --tb=short
-
-# Bash integration tests (requires bats-core)
-brew install bats-core       # one-time setup
-bats test/                   # run all tests
 ```
 
 ## License

{overkill-0.4.0 → overkill-0.5.0}/README.md

@@ -50,7 +50,7 @@ You need these to participate in the madness:
 
 **Runtime**:
 
-- [Python](https://www.python.org/) 3.12+ — for the `overkill` CLI
+- [Python](https://www.python.org/) 3.11+ — for the `overkill` CLI
 - [Node.js](https://nodejs.org/) v18+ — Codex and Claude Code CLI are npm packages, so yes, you need this
 - A fast credit card — essential
 
@@ -370,12 +370,7 @@ uv run mypy src/
 ## Testing
 
 ```bash
-# Python tests
 uv run pytest --tb=short
-
-# Bash integration tests (requires bats-core)
-brew install bats-core       # one-time setup
-bats test/                   # run all tests
 ```
 
 ## License

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/claude-refactor-full.prompt.md

@@ -35,11 +35,11 @@ You are a refactoring advisor analyzing an entire codebase for **architecture-le
 
 ```json
 {
-  "title": "[P1] Invert dependency: review-loop.sh hardcodes AI provider details",
-  "body": "Currently `bin/review-loop.sh` directly calls OpenAI/Claude APIs with provider-specific logic scattered across lines 150-220, 340-380, and 450-490. This means:\n- Adding a new AI provider requires modifying 3 sections of a 700-line file\n- Testing with a mock provider is impossible without editing production code\n- Provider-specific retry/error logic is interleaved with review orchestration\n\n**Suggested structure**: Extract a `lib/ai-provider.sh` interface with `call_ai()` that encapsulates provider selection, API calls, and retries. `review-loop.sh` calls only `call_ai()` and doesn't know which provider is behind it.\n\n**Rollback**: If `lib/ai-provider.sh` causes issues, revert the single file and restore inline calls — the orchestration logic in review-loop.sh doesn't change.",
+  "title": "[P1] Invert dependency: loop_engine hardcodes AI provider details",
+  "body": "Currently `src/mr_overkill/loop_engine.py` directly calls AI CLI tools with provider-specific logic scattered across lines 150-220, 340-380, and 450-490. This means:\n- Adding a new AI provider requires modifying 3 sections of a 700-line file\n- Testing with a mock provider is impossible without editing production code\n- Provider-specific retry/error logic is interleaved with review orchestration\n\n**Suggested structure**: Extract a Protocol-based `AIProvider` interface with `call()` that encapsulates provider selection, API calls, and retries. `loop_engine.py` calls only the Protocol and doesn't know which provider is behind it.\n\n**Rollback**: If the Protocol abstraction causes issues, revert the single file and restore inline calls — the orchestration logic in loop_engine.py doesn't change.",
   "confidence_score": 0.8,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 150, "end": 220} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 150, "end": 220} }
 }
 ```
 
@@ -51,7 +51,7 @@ You are a refactoring advisor analyzing an entire codebase for **architecture-le
   "body": "The codebase would benefit from separating concerns into Model-View-Controller layers for better organization.",
   "confidence_score": 0.5,
   "priority": 2,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 700} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 1, "end": 700} }
 }
 ```
 Why this is bad: no concrete impact statement, no evidence of current pain, suggests a pattern without demonstrating need, no phased migration.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/claude-refactor-layer.prompt.md

@@ -35,11 +35,11 @@ You are a refactoring advisor analyzing an entire codebase for **layer-level** (
 
 ```json
 {
-  "title": "[P1] Unify error exit pattern across all bin/ scripts",
-  "body": "Error exits are handled 3 different ways:\n1. `bin/review-loop.sh` uses `die()` (lines 25-28) which logs to stderr and exits 1\n2. `bin/refactor-suggest.sh` uses `log_error` + bare `exit 1` (lines 88, 142, 201)\n3. `bin/apply-fix.sh` calls `echo \"ERROR: ...\" >&2` directly (lines 33, 67)\n\nThis makes it easy to miss cleanup (temp file removal) on error paths. A coordinated change to use a shared `die()` that includes cleanup would prevent resource leaks across all scripts.",
+  "title": "[P1] Unify error handling pattern across orchestration modules",
+  "body": "Error handling is done 3 different ways:\n1. `src/mr_overkill/review_loop.py` raises `SystemExit` (lines 30-35) with stderr logging\n2. `src/mr_overkill/refactor_suggest.py` uses `logger.error` + bare `sys.exit(1)` (lines 88, 142, 201)\n3. `src/mr_overkill/retry.py` raises `RuntimeError` directly (lines 45, 78)\n\nThis makes it easy to miss cleanup (temp file removal) on error paths. A coordinated change to use a shared exception hierarchy with cleanup hooks would prevent resource leaks across all modules.",
   "confidence_score": 0.85,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 25, "end": 28} }
+  "code_location": { "file_path": "src/mr_overkill/review_loop.py", "line_range": {"start": 30, "end": 35} }
 }
 ```
 
@@ -51,7 +51,7 @@ You are a refactoring advisor analyzing an entire codebase for **layer-level** (
   "body": "The codebase could benefit from more consistent error handling patterns.",
   "confidence_score": 0.5,
   "priority": 2,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 700} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 1, "end": 700} }
 }
 ```
 Why this is bad: no specific examples of inconsistency, no file/line citations, doesn't explain why a coordinated change is needed.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/claude-refactor-micro.prompt.md

@@ -37,10 +37,10 @@ You are a refactoring advisor analyzing an entire codebase for **micro-level** i
 ```json
 {
   "title": "[P1] Extract duplicated validation into shared helper in process_input()",
-  "body": "Lines 42-58 and 103-119 of `bin/review-loop.sh` contain identical input validation logic (same 3 conditions, same error messages). Extracting into a `validate_input()` function eliminates the duplication and ensures future validation changes are applied consistently.",
+  "body": "Lines 55-70 and 130-145 of `src/mr_overkill/loop_engine.py` contain identical iteration-result validation logic (same 3 conditions, same error messages). Extracting into a `_validate_iteration()` helper eliminates the duplication and ensures future validation changes are applied consistently.",
   "confidence_score": 0.9,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 42, "end": 58} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 55, "end": 70} }
 }
 ```
 
@@ -52,7 +52,7 @@ You are a refactoring advisor analyzing an entire codebase for **micro-level** i
   "body": "This code could benefit from the Strategy pattern for better flexibility.",
   "confidence_score": 0.5,
   "priority": 3,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 200} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 1, "end": 200} }
 }
 ```
 Why this is bad: vague, no specific code reference, no measurable benefit, suggests an architecture-level change.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/claude-refactor-module.prompt.md

@@ -35,10 +35,10 @@ You are a refactoring advisor analyzing an entire codebase for **module-level**
 ```json
 {
   "title": "[P1] Extract repeated JSON validation into shared validate_json()",
-  "body": "The same jq-based JSON validation logic appears in `bin/review-loop.sh` (lines 120-135), `bin/refactor-suggest.sh` (lines 45-60), and `bin/apply-fix.sh` (lines 30-42). All three copies check for valid JSON, extract `.findings`, and handle parse errors — but the error messages have already diverged (review-loop prints to stderr, the others use `log_error`). Extracting to `lib/json-utils.sh:validate_json()` eliminates the duplication and unifies error handling.",
+  "body": "The same JSON validation logic appears in `src/example/ingest.py` (lines 12-27), `src/example/export.py` (lines 50-65), and `src/example/validate.py` (lines 8-20). All three copies parse review JSON, extract `findings`, and handle parse errors — but the error messages have already diverged. Extracting to `src/example/json_utils.py:parse_review_json()` eliminates the duplication and unifies error handling.",
   "confidence_score": 0.85,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 120, "end": 135} }
+  "code_location": { "file_path": "src/example/ingest.py", "line_range": {"start": 12, "end": 27} }
 }
 ```
 
@@ -50,7 +50,7 @@ You are a refactoring advisor analyzing an entire codebase for **module-level**
   "body": "Several files handle errors similarly. Consider creating a shared error handler.",
   "confidence_score": 0.6,
   "priority": 2,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 500} }
+  "code_location": { "file_path": "src/mr_overkill/review_loop.py", "line_range": {"start": 1, "end": 500} }
 }
 ```
 Why this is bad: doesn't specify which files, doesn't cite line numbers, doesn't explain what's duplicated or how copies have diverged.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/claude-review.prompt.md

@@ -6,6 +6,8 @@ You are a code reviewer analyzing a proposed change.
 - **Target branch**: ${TARGET_BRANCH}
 - **Review iteration**: ${ITERATION}
 
+${REVIEWER_CONTEXT}
+
 ## Instructions
 
 Start by running the following command to get the diff:

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/codex-refactor-full.prompt.md

@@ -35,11 +35,11 @@ You are a refactoring advisor analyzing an entire codebase for **architecture-le
 
 ```json
 {
-  "title": "[P1] Invert dependency: review-loop.sh hardcodes AI provider details",
-  "body": "Currently `bin/review-loop.sh` directly calls OpenAI/Claude APIs with provider-specific logic scattered across lines 150-220, 340-380, and 450-490. This means:\n- Adding a new AI provider requires modifying 3 sections of a 700-line file\n- Testing with a mock provider is impossible without editing production code\n- Provider-specific retry/error logic is interleaved with review orchestration\n\n**Suggested structure**: Extract a `lib/ai-provider.sh` interface with `call_ai()` that encapsulates provider selection, API calls, and retries. `review-loop.sh` calls only `call_ai()` and doesn't know which provider is behind it.\n\n**Rollback**: If `lib/ai-provider.sh` causes issues, revert the single file and restore inline calls — the orchestration logic in review-loop.sh doesn't change.",
+  "title": "[P1] Invert dependency: loop_engine hardcodes AI provider details",
+  "body": "Currently `src/mr_overkill/loop_engine.py` directly calls AI CLI tools with provider-specific logic scattered across lines 150-220, 340-380, and 450-490. This means:\n- Adding a new AI provider requires modifying 3 sections of a 700-line file\n- Testing with a mock provider is impossible without editing production code\n- Provider-specific retry/error logic is interleaved with review orchestration\n\n**Suggested structure**: Extract a Protocol-based `AIProvider` interface with `call()` that encapsulates provider selection, API calls, and retries. `loop_engine.py` calls only the Protocol and doesn't know which provider is behind it.\n\n**Rollback**: If the Protocol abstraction causes issues, revert the single file and restore inline calls — the orchestration logic in loop_engine.py doesn't change.",
   "confidence_score": 0.8,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 150, "end": 220} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 150, "end": 220} }
 }
 ```
 
@@ -51,7 +51,7 @@ You are a refactoring advisor analyzing an entire codebase for **architecture-le
   "body": "The codebase would benefit from separating concerns into Model-View-Controller layers for better organization.",
   "confidence_score": 0.5,
   "priority": 2,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 700} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 1, "end": 700} }
 }
 ```
 Why this is bad: no concrete impact statement, no evidence of current pain, suggests a pattern without demonstrating need, no phased migration.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/codex-refactor-layer.prompt.md

@@ -35,11 +35,11 @@ You are a refactoring advisor analyzing an entire codebase for **layer-level** (
 
 ```json
 {
-  "title": "[P1] Unify error exit pattern across all bin/ scripts",
-  "body": "Error exits are handled 3 different ways:\n1. `bin/review-loop.sh` uses `die()` (lines 25-28) which logs to stderr and exits 1\n2. `bin/refactor-suggest.sh` uses `log_error` + bare `exit 1` (lines 88, 142, 201)\n3. `bin/apply-fix.sh` calls `echo \"ERROR: ...\" >&2` directly (lines 33, 67)\n\nThis makes it easy to miss cleanup (temp file removal) on error paths. A coordinated change to use a shared `die()` that includes cleanup would prevent resource leaks across all scripts.",
+  "title": "[P1] Unify error handling pattern across orchestration modules",
+  "body": "Error handling is done 3 different ways:\n1. `src/mr_overkill/review_loop.py` raises `SystemExit` (lines 30-35) with stderr logging\n2. `src/mr_overkill/refactor_suggest.py` uses `logger.error` + bare `sys.exit(1)` (lines 88, 142, 201)\n3. `src/mr_overkill/retry.py` raises `RuntimeError` directly (lines 45, 78)\n\nThis makes it easy to miss cleanup (temp file removal) on error paths. A coordinated change to use a shared exception hierarchy with cleanup hooks would prevent resource leaks across all modules.",
   "confidence_score": 0.85,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 25, "end": 28} }
+  "code_location": { "file_path": "src/mr_overkill/review_loop.py", "line_range": {"start": 30, "end": 35} }
 }
 ```
 
@@ -51,7 +51,7 @@ You are a refactoring advisor analyzing an entire codebase for **layer-level** (
   "body": "The codebase could benefit from more consistent error handling patterns.",
   "confidence_score": 0.5,
   "priority": 2,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 700} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 1, "end": 700} }
 }
 ```
 Why this is bad: no specific examples of inconsistency, no file/line citations, doesn't explain why a coordinated change is needed.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/codex-refactor-micro.prompt.md

@@ -37,10 +37,10 @@ You are a refactoring advisor analyzing an entire codebase for **micro-level** i
 ```json
 {
   "title": "[P1] Extract duplicated validation into shared helper in process_input()",
-  "body": "Lines 42-58 and 103-119 of `bin/review-loop.sh` contain identical input validation logic (same 3 conditions, same error messages). Extracting into a `validate_input()` function eliminates the duplication and ensures future validation changes are applied consistently.",
+  "body": "Lines 55-70 and 130-145 of `src/mr_overkill/loop_engine.py` contain identical iteration-result validation logic (same 3 conditions, same error messages). Extracting into a `_validate_iteration()` helper eliminates the duplication and ensures future validation changes are applied consistently.",
   "confidence_score": 0.9,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 42, "end": 58} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 55, "end": 70} }
 }
 ```
 
@@ -52,7 +52,7 @@ You are a refactoring advisor analyzing an entire codebase for **micro-level** i
   "body": "This code could benefit from the Strategy pattern for better flexibility.",
   "confidence_score": 0.5,
   "priority": 3,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 200} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 1, "end": 200} }
 }
 ```
 Why this is bad: vague, no specific code reference, no measurable benefit, suggests an architecture-level change.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/codex-refactor-module.prompt.md

@@ -35,10 +35,10 @@ You are a refactoring advisor analyzing an entire codebase for **module-level**
 ```json
 {
   "title": "[P1] Extract repeated JSON validation into shared validate_json()",
-  "body": "The same jq-based JSON validation logic appears in `bin/review-loop.sh` (lines 120-135), `bin/refactor-suggest.sh` (lines 45-60), and `bin/apply-fix.sh` (lines 30-42). All three copies check for valid JSON, extract `.findings`, and handle parse errors — but the error messages have already diverged (review-loop prints to stderr, the others use `log_error`). Extracting to `lib/json-utils.sh:validate_json()` eliminates the duplication and unifies error handling.",
+  "body": "The same JSON validation logic appears in `src/example/ingest.py` (lines 12-27), `src/example/export.py` (lines 50-65), and `src/example/validate.py` (lines 8-20). All three copies parse review JSON, extract `findings`, and handle parse errors — but the error messages have already diverged. Extracting to `src/example/json_utils.py:parse_review_json()` eliminates the duplication and unifies error handling.",
   "confidence_score": 0.85,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 120, "end": 135} }
+  "code_location": { "file_path": "src/example/ingest.py", "line_range": {"start": 12, "end": 27} }
 }
 ```
 
@@ -50,7 +50,7 @@ You are a refactoring advisor analyzing an entire codebase for **module-level**
   "body": "Several files handle errors similarly. Consider creating a shared error handler.",
   "confidence_score": 0.6,
   "priority": 2,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 500} }
+  "code_location": { "file_path": "src/mr_overkill/review_loop.py", "line_range": {"start": 1, "end": 500} }
 }
 ```
 Why this is bad: doesn't specify which files, doesn't cite line numbers, doesn't explain what's duplicated or how copies have diverged.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/codex-review.prompt.md

@@ -6,6 +6,8 @@ You are a code reviewer analyzing a proposed change.
 - **Target branch**: ${TARGET_BRANCH}
 - **Review iteration**: ${ITERATION}
 
+${REVIEWER_CONTEXT}
+
 ## Instructions
 
 Run the following command to get the diff:

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/gemini-refactor-full.prompt.md

@@ -35,11 +35,11 @@ You are a refactoring advisor analyzing an entire codebase for **architecture-le
 
 ```json
 {
-  "title": "[P1] Invert dependency: review-loop.sh hardcodes AI provider details",
-  "body": "Currently `bin/review-loop.sh` directly calls OpenAI/Claude APIs with provider-specific logic scattered across lines 150-220, 340-380, and 450-490. This means:\n- Adding a new AI provider requires modifying 3 sections of a 700-line file\n- Testing with a mock provider is impossible without editing production code\n- Provider-specific retry/error logic is interleaved with review orchestration\n\n**Suggested structure**: Extract a `lib/ai-provider.sh` interface with `call_ai()` that encapsulates provider selection, API calls, and retries. `review-loop.sh` calls only `call_ai()` and doesn't know which provider is behind it.\n\n**Rollback**: If `lib/ai-provider.sh` causes issues, revert the single file and restore inline calls — the orchestration logic in review-loop.sh doesn't change.",
+  "title": "[P1] Invert dependency: loop_engine hardcodes AI provider details",
+  "body": "Currently `src/mr_overkill/loop_engine.py` directly calls AI CLI tools with provider-specific logic scattered across lines 150-220, 340-380, and 450-490. This means:\n- Adding a new AI provider requires modifying 3 sections of a 700-line file\n- Testing with a mock provider is impossible without editing production code\n- Provider-specific retry/error logic is interleaved with review orchestration\n\n**Suggested structure**: Extract a Protocol-based `AIProvider` interface with `call()` that encapsulates provider selection, API calls, and retries. `loop_engine.py` calls only the Protocol and doesn't know which provider is behind it.\n\n**Rollback**: If the Protocol abstraction causes issues, revert the single file and restore inline calls — the orchestration logic in loop_engine.py doesn't change.",
   "confidence_score": 0.8,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 150, "end": 220} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 150, "end": 220} }
 }
 ```
 
@@ -51,7 +51,7 @@ You are a refactoring advisor analyzing an entire codebase for **architecture-le
   "body": "The codebase would benefit from separating concerns into Model-View-Controller layers for better organization.",
   "confidence_score": 0.5,
   "priority": 2,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 700} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 1, "end": 700} }
 }
 ```
 Why this is bad: no concrete impact statement, no evidence of current pain, suggests a pattern without demonstrating need, no phased migration.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/gemini-refactor-layer.prompt.md

@@ -35,11 +35,11 @@ You are a refactoring advisor analyzing an entire codebase for **layer-level** (
 
 ```json
 {
-  "title": "[P1] Unify error exit pattern across all bin/ scripts",
-  "body": "Error exits are handled 3 different ways:\n1. `bin/review-loop.sh` uses `die()` (lines 25-28) which logs to stderr and exits 1\n2. `bin/refactor-suggest.sh` uses `log_error` + bare `exit 1` (lines 88, 142, 201)\n3. `bin/apply-fix.sh` calls `echo \"ERROR: ...\" >&2` directly (lines 33, 67)\n\nThis makes it easy to miss cleanup (temp file removal) on error paths. A coordinated change to use a shared `die()` that includes cleanup would prevent resource leaks across all scripts.",
+  "title": "[P1] Unify error handling pattern across orchestration modules",
+  "body": "Error handling is done 3 different ways:\n1. `src/mr_overkill/review_loop.py` raises `SystemExit` (lines 30-35) with stderr logging\n2. `src/mr_overkill/refactor_suggest.py` uses `logger.error` + bare `sys.exit(1)` (lines 88, 142, 201)\n3. `src/mr_overkill/retry.py` raises `RuntimeError` directly (lines 45, 78)\n\nThis makes it easy to miss cleanup (temp file removal) on error paths. A coordinated change to use a shared exception hierarchy with cleanup hooks would prevent resource leaks across all modules.",
   "confidence_score": 0.85,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 25, "end": 28} }
+  "code_location": { "file_path": "src/mr_overkill/review_loop.py", "line_range": {"start": 30, "end": 35} }
 }
 ```
 
@@ -51,7 +51,7 @@ You are a refactoring advisor analyzing an entire codebase for **layer-level** (
   "body": "The codebase could benefit from more consistent error handling patterns.",
   "confidence_score": 0.5,
   "priority": 2,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 700} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 1, "end": 700} }
 }
 ```
 Why this is bad: no specific examples of inconsistency, no file/line citations, doesn't explain why a coordinated change is needed.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/gemini-refactor-micro.prompt.md

@@ -37,10 +37,10 @@ You are a refactoring advisor analyzing an entire codebase for **micro-level** i
 ```json
 {
   "title": "[P1] Extract duplicated validation into shared helper in process_input()",
-  "body": "Lines 42-58 and 103-119 of `bin/review-loop.sh` contain identical input validation logic (same 3 conditions, same error messages). Extracting into a `validate_input()` function eliminates the duplication and ensures future validation changes are applied consistently.",
+  "body": "Lines 55-70 and 130-145 of `src/mr_overkill/loop_engine.py` contain identical iteration-result validation logic (same 3 conditions, same error messages). Extracting into a `_validate_iteration()` helper eliminates the duplication and ensures future validation changes are applied consistently.",
   "confidence_score": 0.9,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 42, "end": 58} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 55, "end": 70} }
 }
 ```
 
@@ -52,7 +52,7 @@ You are a refactoring advisor analyzing an entire codebase for **micro-level** i
   "body": "This code could benefit from the Strategy pattern for better flexibility.",
   "confidence_score": 0.5,
   "priority": 3,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 200} }
+  "code_location": { "file_path": "src/mr_overkill/loop_engine.py", "line_range": {"start": 1, "end": 200} }
 }
 ```
 Why this is bad: vague, no specific code reference, no measurable benefit, suggests an architecture-level change.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/gemini-refactor-module.prompt.md

@@ -35,10 +35,10 @@ You are a refactoring advisor analyzing an entire codebase for **module-level**
 ```json
 {
   "title": "[P1] Extract repeated JSON validation into shared validate_json()",
-  "body": "The same jq-based JSON validation logic appears in `bin/review-loop.sh` (lines 120-135), `bin/refactor-suggest.sh` (lines 45-60), and `bin/apply-fix.sh` (lines 30-42). All three copies check for valid JSON, extract `.findings`, and handle parse errors — but the error messages have already diverged (review-loop prints to stderr, the others use `log_error`). Extracting to `lib/json-utils.sh:validate_json()` eliminates the duplication and unifies error handling.",
+  "body": "The same JSON validation logic appears in `src/example/ingest.py` (lines 12-27), `src/example/export.py` (lines 50-65), and `src/example/validate.py` (lines 8-20). All three copies parse review JSON, extract `findings`, and handle parse errors — but the error messages have already diverged. Extracting to `src/example/json_utils.py:parse_review_json()` eliminates the duplication and unifies error handling.",
   "confidence_score": 0.85,
   "priority": 1,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 120, "end": 135} }
+  "code_location": { "file_path": "src/example/ingest.py", "line_range": {"start": 12, "end": 27} }
 }
 ```
 
@@ -50,7 +50,7 @@ You are a refactoring advisor analyzing an entire codebase for **module-level**
   "body": "Several files handle errors similarly. Consider creating a shared error handler.",
   "confidence_score": 0.6,
   "priority": 2,
-  "code_location": { "file_path": "bin/review-loop.sh", "line_range": {"start": 1, "end": 500} }
+  "code_location": { "file_path": "src/mr_overkill/review_loop.py", "line_range": {"start": 1, "end": 500} }
 }
 ```
 Why this is bad: doesn't specify which files, doesn't cite line numbers, doesn't explain what's duplicated or how copies have diverged.

{overkill-0.4.0 → overkill-0.5.0}/prompts/active/gemini-review.prompt.md

@@ -6,6 +6,8 @@ You are a code reviewer analyzing a proposed change.
 - **Target branch**: ${TARGET_BRANCH}
 - **Review iteration**: ${ITERATION}
 
+${REVIEWER_CONTEXT}
+
 ## Instructions
 
 Start by running the following command to get the diff:

{overkill-0.4.0 → overkill-0.5.0}/pyproject.toml

@@ -1,10 +1,10 @@
 [project]
 name = "overkill"
-version = "0.4.0"
+version = "0.5.0"
 description = "AI-powered code review loop — automates Codex review + Claude fix cycles"
 readme = "README.md"
 license = { text = "MIT" }
-requires-python = ">=3.12"
+requires-python = ">=3.11"
 authors = [{ name = "ModocAI" }]
 keywords = ["code-review", "refactoring", "ai", "claude", "codex", "automation"]
 classifiers = [
@@ -14,6 +14,7 @@ classifiers = [
     "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
     "Topic :: Software Development :: Quality Assurance",
@@ -44,14 +45,14 @@ testpaths = ["tests"]
 pythonpath = ["src"]
 
 [tool.ruff]
-target-version = "py312"
+target-version = "py311"
 src = ["src", "tests"]
 
 [tool.ruff.lint]
 select = ["E", "F", "I", "UP", "B", "SIM", "RUF"]
 
 [tool.mypy]
-python_version = "3.12"
+python_version = "3.11"
 strict = true
 warn_return_any = true
 warn_unused_configs = true

{overkill-0.4.0 → overkill-0.5.0}/src/mr_overkill/agents.py

@@ -38,6 +38,13 @@ from mr_overkill.two_step_fix import claude_two_step_fix
 logger = logging.getLogger(__name__)
 
 
+def _format_reviewer_context(raw: str) -> str:
+    """Wrap non-empty reviewer context in a markdown section."""
+    if not raw:
+        return ""
+    return f"## Author Context\n\n{raw}"
+
+
 # ── Budget / retry helpers (moved from review_loop.py) ───────────────
 
 
@@ -167,6 +174,7 @@ class CodexReviewAgent(ReviewAgent):
             "CURRENT_BRANCH": config.current_branch,
             "TARGET_BRANCH": config.target_branch,
             "ITERATION": str(iteration),
+            "REVIEWER_CONTEXT": _format_reviewer_context(config.reviewer_context),
         })
 
         if not self._budget_fn("codex", config.budget_scope, 0):
@@ -268,6 +276,7 @@ class ClaudeReviewAgent(ReviewAgent):
             "CURRENT_BRANCH": config.current_branch,
             "TARGET_BRANCH": config.target_branch,
             "ITERATION": str(iteration),
+            "REVIEWER_CONTEXT": _format_reviewer_context(config.reviewer_context),
         })
 
         if not self._budget_fn("claude", config.budget_scope, 0):
@@ -365,6 +374,7 @@ class GeminiReviewAgent(ReviewAgent):
             "CURRENT_BRANCH": config.current_branch,
             "TARGET_BRANCH": config.target_branch,
             "ITERATION": str(iteration),
+            "REVIEWER_CONTEXT": _format_reviewer_context(config.reviewer_context),
         })
 
         if not self._budget_fn("gemini", config.budget_scope, 0):

{overkill-0.4.0 → overkill-0.5.0}/src/mr_overkill/classify.py

@@ -1,7 +1,4 @@
-"""Error classification for CLI command failures.
-
-Ports ``_classify_cli_error`` from ``bin/lib/retry.sh`` to Python.
-"""
+"""Error classification for CLI command failures."""
 
 from __future__ import annotations
 

{overkill-0.4.0 → overkill-0.5.0}/src/mr_overkill/cli.py

@@ -108,13 +108,14 @@ def _load_rc_file(rc_name: str) -> dict[str, str]:
         "RETRY_INITIAL_WAIT", "BUDGET_SCOPE", "DIAGNOSTIC_LOG",
         "SCOPE", "AUTO_APPROVE", "CREATE_PR", "WITH_REVIEW",
         "REVIEW_LOOPS", "FIX_NITS", "REVIEWER_BACKEND",
+        "REVIEWER_CONTEXT",
     }
     boolean_keys = {
         "DRY_RUN", "AUTO_COMMIT", "DIAGNOSTIC_LOG",
         "AUTO_APPROVE", "CREATE_PR", "WITH_REVIEW", "FIX_NITS",
     }
     kv_re = re.compile(
-        r"^\s*(\w+)=[\"']?([^\"']*)[\"']?\s*$"
+        r"""^\s*(\w+)=(?:"([^"]*)"|'([^']*)'|(.*?))\s*$"""
     )
     values: dict[str, str] = {}
 
@@ -124,7 +125,7 @@ def _load_rc_file(rc_name: str) -> dict[str, str]:
             continue
         m = kv_re.match(line)
         if m and m.group(1) in allowed_keys:
-            key, val = m.group(1), m.group(2).strip()
+            key, val = m.group(1), (m.group(2) or m.group(3) or m.group(4) or "").strip()
             if key in boolean_keys and val.lower() not in ("true", "false"):
                 msg = f"{rc_path.name}: {key} must be 'true' or 'false', got '{val}'."
                 raise SystemExit(f"Error: {msg}")
@@ -299,6 +300,11 @@ def parse_review_loop_args(
         choices=["claude", "codex", "gemini"],
         help="Backend for code review (default: codex)",
     )
+    parser.add_argument(
+        "--context",
+        default=None,
+        help="Additional context for the reviewer (e.g. design intent, constraints)",
+    )
 
     args = parser.parse_args(argv)
 
@@ -394,6 +400,10 @@ def parse_review_loop_args(
             saved = log_dir / "reviewer-backend.txt"
             if saved.is_file():
                 args.reviewer_backend = saved.read_text().strip()
+        if args.context is None:
+            saved = log_dir / "reviewer-context.txt"
+            if saved.is_file():
+                args.context = saved.read_text().strip()
 
     if max_loop is not None and max_loop < 1:
         parser.error("--max-loop must be a positive integer")
@@ -405,6 +415,10 @@ def parse_review_loop_args(
             f" got {reviewer_backend!r}"
         )
 
+    reviewer_context = (
+        args.context if args.context is not None else rc.get("REVIEWER_CONTEXT", "")
+    )
+
     return LoopConfig(
         current_branch=current_branch,
         target_branch=target,
@@ -425,6 +439,7 @@ def parse_review_loop_args(
         prompts_dir=prompts_dir,
         pr_number=pr_number,
         reviewer_backend=reviewer_backend,
+        reviewer_context=reviewer_context,
     )
 
 

{overkill-0.4.0 → overkill-0.5.0}/src/mr_overkill/loop_engine.py

@@ -1,8 +1,5 @@
 """Unified review-fix loop engine.
 
-Consolidates the common loop pattern from review-loop.sh,
-refactor-suggest.sh, and self-review.sh into a single reusable engine.
-
 Uses Protocol-based DI for external operations (fix, review, budget)
 and imports Wave 1 modules directly for JSON parsing, git ops, and reporting.
 """
@@ -613,7 +610,7 @@ def _no_diff(target: str, current: str, cwd: Path | None) -> bool:
 def _clean_stale_logs(log_dir: Path) -> None:
     """Remove iteration artifacts from prior runs.
 
-    Mirrors the cleanup in ``bin/review-loop.sh`` so that fresh runs
+    Cleanup stale log files from previous runs so that fresh runs
     do not mix stale review/fix/summary files into new results.
     """
     patterns = [
@@ -638,6 +635,7 @@ def _save_metadata(config: LoopConfig, cwd: Path | None) -> None:
     (log_dir / "target-branch.txt").write_text(config.target_branch)
     (log_dir / "max-loop.txt").write_text(str(config.max_loop))
     (log_dir / "reviewer-backend.txt").write_text(config.reviewer_backend)
+    (log_dir / "reviewer-context.txt").write_text(config.reviewer_context)
     if config.scope:
         (log_dir / "scope.txt").write_text(config.scope)