aida-mcp 0.1.2.dev1__tar.gz

aida_mcp-0.1.2.dev1/.gitignore

@@ -0,0 +1,45 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+env/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+reports/
+
+# Logs
+*.log
+

aida_mcp-0.1.2.dev1/PKG-INFO

@@ -0,0 +1,193 @@
+Metadata-Version: 2.4
+Name: aida-mcp
+Version: 0.1.2.dev1
+Summary: AIDA MCP server - Developer actions (lint, test, typecheck) for monorepos
+Author-email: GoodData Corporation <support@gooddata.com>
+Requires-Python: <3.14,>=3.12
+Requires-Dist: httpx>=0.28.0
+Requires-Dist: junitparser>=3.1.2
+Requires-Dist: langchain-text-splitters>=0.2.0
+Requires-Dist: mcp>=1.25.0
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: orjson>=3.11.5
+Requires-Dist: pydantic>=2.10.6
+Requires-Dist: pyyaml>=6.0.1
+Requires-Dist: sentence-transformers>=3.0.0
+Requires-Dist: structlog>=25.3.0
+Requires-Dist: torch>=2.9.0
+Description-Content-Type: text/markdown
+
+# AIDA (AI Developer Assistant)
+
+FastMCP server (`aida-mcp`) that exposes GoodData's **unified validation** workflow (plus GitHub helpers and rules retrieval) over the MCP protocol. Use it from Cursor, Claude Code, JetBrains AI, or the CLI to run repo-configured lint/type/test/codegen pipelines without memorizing each project's workflow.
+
+---
+
+## TL;DR – Getting Started
+
+### Cursor / Claude Code / JetBrains AI
+| Step | Command | Notes |
+| --- | --- | --- |
+| 1 | `cd packages/aida-mcp && make install` | Installs/updates the **packaged** MCP server (wheel) only. |
+| 2 | `aida-mcp init` (run in your repo root) | Writes **repo-local** MCP config stubs (e.g. `.cursor/mcp.json`, `.mcp.json`) and onboarding files. Add `--vendor-rules` to enable vendor/example embedded rules. |
+| 3 | Restart IDE / Agent | Tools appear as `aida` in the MCP panel. |
+| 4 | Ask your assistant to "validate <service>" | The assistant calls the right tool automatically. |
+
+Need the full local setup (Node, uv, multi-repo tips, troubleshooting)? See [CONTRIBUTING.md](CONTRIBUTING.md).
+
+---
+
+## Repo Config Files
+
+AIDA reads repo-owned policy and routing from `.aida/`:
+- `change_domains.yaml`
+- `validation_policy.yaml`
+- `validation_registry.yaml`
+- `git_policy.yaml` (commit/PR/workflow knobs for git-related tools)
+- `rules/**/*.mdc`
+
+`aida-mcp init` bootstraps these files when missing.
+
+---
+
+## Tool Overview
+
+| Tool | Highlights |
+| --- | --- |
+| `validate` | Unified validation tool. Computes scope (`pre_commit` / `pre_push`), routes via `.aida/*`, executes registry-defined commands with streaming progress. |
+| `get_rules` | Retrieves relevant rules for the current task (hybrid lexical + embeddings), with transparent scoring/debug output. |
+| `github_ci_errors` | Fetch size-capped CI failures for a PR (errors-only by default). |
+| `github_comments` | List/reply/resolve PR review threads (non-interactive). |
+
+**Progress Tracking**: `validate` streams real-time progress updates to Cursor using combined `ctx.report_progress()` + `ctx.info()` events. External validators can emit `AIDA_EVENT {json}` lines for richer progress while keeping full logs in artifacts.
+
+Detailed behavior (step descriptions, parameters, and usage snippets) now lives in [docs/validation-tools.md](docs/validation-tools.md) to keep this README short.
+If you only need the external command contract and config shape, start with [docs/external-validation-interface.md](docs/external-validation-interface.md).
+Rules retrieval details live in [docs/rules-retrieval.md](docs/rules-retrieval.md).
+
+---
+
+## Architecture at a Glance
+
+```
+packages/aida-mcp/
+├── src/
+│   └── app/
+│       ├── server/              # FastMCP entrypoint + tool registration
+│       ├── tools/
+│       │   ├── core/            # shared primitives (registry, change classifier, external tool helpers)
+│       │   └── validate/        # unified validate engine (policy + external command execution)
+│       └── utils/               # command runner, config loader, junit parsing, progress, timing, etc.
+├── config/                      # bundled defaults (registry, tool configs)
+├── docs/                        # detailed validation tool documentation
+├── tests/                       # unit + integration suites
+└── CONTRIBUTING.md              # setup, workflows, troubleshooting
+```
+
+Validation design:
+- AIDA is language-agnostic for validation command execution.
+- Validation commands are repo-owned external executables configured in `.aida/validation_registry.yaml`.
+- Output processors remain built-in and reusable inside `packages/aida-mcp`.
+
+---
+
+## Using the Tools
+
+### From Cursor / Claude
+1. Install/update the MCP server via `cd packages/aida-mcp && make install`.
+2. Onboard the repo you want to use AIDA in via `aida-mcp init` (run in the repo root).
+2. In the editor, ask: “run validation” or “validate `microservices/gen-ai`”. The assistant calls `validate(scope=..., focus_paths=...)`.
+3. Routing and the exact commands run are repo-owned via `.aida/*`.
+
+### From the terminal
+
+```bash
+cd packages/aida-mcp
+aida-mcp  # launches stdio server manually (once installed via uv tool)
+```
+
+Commit helper (enforces footer policy and 70-char subject limit):
+
+```bash
+aida-mcp commit \
+  --type chore \
+  --scope aida \
+  --title "add commit helper command" \
+  --body "Enforce risk footer ordering and metadata trailers." \
+  --jira DX-123 \
+  --risk nonprod
+```
+
+Prefer running the command directly in this shape; do not probe with `aida-mcp commit --help` unless troubleshooting.
+
+Optional metadata in the footer block:
+- `--co-authored-by "Name <email>"` (repeatable)
+- `--ai-share actor=percent` (repeatable, must sum to 100)
+- `--ai-share-auto <actor>` for deterministic `<actor>=100` without guessing (policy-gated)
+- multiline body support:
+  - `--body-file /path/to/body.txt`
+  - `--body-stdin` (pipe or heredoc)
+  - `--body-line ...` (repeatable)
+
+`aida-mcp commit` policy values (for example title length, allowed `risk:` values, and optional required trailers) are configurable via `.aida/git_policy.yaml`.
+`Co-authored-by` is explicit-only: pass `--co-authored-by` when available; if omitted, no co-author trailer is added.
+
+Validation CLI shortcuts still live in the repo root:
+
+```bash
+make format-fix lint-fix
+make types
+make test
+make validate       # fast default (format/lint/types + unit tests)
+make validate-all   # includes integration tests (slow)
+```
+
+---
+
+## Troubleshooting & Workflow Guides
+
+Rather than duplicating multiple pages of instructions here, refer to:
+- [CONTRIBUTING.md](CONTRIBUTING.md): environment prep, Cursor integration, node/uv requirements, manual overrides, and how to add new tools/rules.
+- [docs/validation-tools.md](docs/validation-tools.md): deep dive into each tool’s steps, parameters, and best practices.
+- Developer onboarding docs under `docs/developer/` for broader GoodData setup.
+
+---
+
+## FAQ
+
+**Why a single `validate` tool?**
+Repo-owned routing (`.aida/*`) lets `aida-mcp` live in a separate repo while still executing GoodData-specific validations (often via external wrappers) with streaming progress.
+
+**Can I add custom output processors as external commands?**
+Not in unified validate today. Processors are built-in only; for custom behavior, either emit JSON consumed by `external_json` or add a new reusable built-in processor in `packages/aida-mcp`.
+
+**Can I run Docker/OpenAPI without rewriting commands?**
+Yes—when the repo’s `.aida/validation_policy.yaml` routes those steps. Add dedicated pipelines/commands for `docker`/`openapi` when needed.
+
+**What happens if the MCP client disconnects during validation?**
+The server gracefully handles invalid or closed MCP contexts. Progress updates are silently skipped if the context becomes unavailable, preventing server crashes. Validation continues to completion and returns results normally.
+
+**What if Python tests fail with "duplicate file name metadata.proto"?**
+The Python validator automatically detects this common issue (stale protobuf artifacts in `.venv`) and runs `make ultra-clean` + `make dev` to rebuild the environment, then retries the test step. This recovery is transparent and only triggers when needed.
+
+**How do I extend validation routing?**
+Update `.aida/change_domains.yaml` + `.aida/validation_policy.yaml`, and add commands in `.aida/validation_registry.yaml` as needed.
+
+---
+
+## Upgrading / breaking changes
+
+When AIDA source changes in a way that affects the MCP server executable, the installed tool set, or the MCP tool schema, you must **reinstall/refresh the MCP server setup** in your client.
+
+- **Action**: rerun `cd packages/aida-mcp && make install`, then restart/reload your client.
+- **Why**: clients cache the MCP server command + environment from MCP config files. Reinstall ensures the client points at the current `aida-mcp` executable and tool definitions.
+
+---
+
+## Repository setup
+
+This repository is AIDA-ready (repo-owned `.aida/` and repo-local MCP stubs are committed), so you can install the tool and start using it immediately.
+
+---
+
+Happy validating! Let the assistants run the noisy commands so you can stay focused on the code. For contributions, open an issue or follow the checklist in [CONTRIBUTING.md](CONTRIBUTING.md).

aida_mcp-0.1.2.dev1/README.md

@@ -0,0 +1,174 @@
+# AIDA (AI Developer Assistant)
+
+FastMCP server (`aida-mcp`) that exposes GoodData's **unified validation** workflow (plus GitHub helpers and rules retrieval) over the MCP protocol. Use it from Cursor, Claude Code, JetBrains AI, or the CLI to run repo-configured lint/type/test/codegen pipelines without memorizing each project's workflow.
+
+---
+
+## TL;DR – Getting Started
+
+### Cursor / Claude Code / JetBrains AI
+| Step | Command | Notes |
+| --- | --- | --- |
+| 1 | `cd packages/aida-mcp && make install` | Installs/updates the **packaged** MCP server (wheel) only. |
+| 2 | `aida-mcp init` (run in your repo root) | Writes **repo-local** MCP config stubs (e.g. `.cursor/mcp.json`, `.mcp.json`) and onboarding files. Add `--vendor-rules` to enable vendor/example embedded rules. |
+| 3 | Restart IDE / Agent | Tools appear as `aida` in the MCP panel. |
+| 4 | Ask your assistant to "validate <service>" | The assistant calls the right tool automatically. |
+
+Need the full local setup (Node, uv, multi-repo tips, troubleshooting)? See [CONTRIBUTING.md](CONTRIBUTING.md).
+
+---
+
+## Repo Config Files
+
+AIDA reads repo-owned policy and routing from `.aida/`:
+- `change_domains.yaml`
+- `validation_policy.yaml`
+- `validation_registry.yaml`
+- `git_policy.yaml` (commit/PR/workflow knobs for git-related tools)
+- `rules/**/*.mdc`
+
+`aida-mcp init` bootstraps these files when missing.
+
+---
+
+## Tool Overview
+
+| Tool | Highlights |
+| --- | --- |
+| `validate` | Unified validation tool. Computes scope (`pre_commit` / `pre_push`), routes via `.aida/*`, executes registry-defined commands with streaming progress. |
+| `get_rules` | Retrieves relevant rules for the current task (hybrid lexical + embeddings), with transparent scoring/debug output. |
+| `github_ci_errors` | Fetch size-capped CI failures for a PR (errors-only by default). |
+| `github_comments` | List/reply/resolve PR review threads (non-interactive). |
+
+**Progress Tracking**: `validate` streams real-time progress updates to Cursor using combined `ctx.report_progress()` + `ctx.info()` events. External validators can emit `AIDA_EVENT {json}` lines for richer progress while keeping full logs in artifacts.
+
+Detailed behavior (step descriptions, parameters, and usage snippets) now lives in [docs/validation-tools.md](docs/validation-tools.md) to keep this README short.
+If you only need the external command contract and config shape, start with [docs/external-validation-interface.md](docs/external-validation-interface.md).
+Rules retrieval details live in [docs/rules-retrieval.md](docs/rules-retrieval.md).
+
+---
+
+## Architecture at a Glance
+
+```
+packages/aida-mcp/
+├── src/
+│   └── app/
+│       ├── server/              # FastMCP entrypoint + tool registration
+│       ├── tools/
+│       │   ├── core/            # shared primitives (registry, change classifier, external tool helpers)
+│       │   └── validate/        # unified validate engine (policy + external command execution)
+│       └── utils/               # command runner, config loader, junit parsing, progress, timing, etc.
+├── config/                      # bundled defaults (registry, tool configs)
+├── docs/                        # detailed validation tool documentation
+├── tests/                       # unit + integration suites
+└── CONTRIBUTING.md              # setup, workflows, troubleshooting
+```
+
+Validation design:
+- AIDA is language-agnostic for validation command execution.
+- Validation commands are repo-owned external executables configured in `.aida/validation_registry.yaml`.
+- Output processors remain built-in and reusable inside `packages/aida-mcp`.
+
+---
+
+## Using the Tools
+
+### From Cursor / Claude
+1. Install/update the MCP server via `cd packages/aida-mcp && make install`.
+2. Onboard the repo you want to use AIDA in via `aida-mcp init` (run in the repo root).
+2. In the editor, ask: “run validation” or “validate `microservices/gen-ai`”. The assistant calls `validate(scope=..., focus_paths=...)`.
+3. Routing and the exact commands run are repo-owned via `.aida/*`.
+
+### From the terminal
+
+```bash
+cd packages/aida-mcp
+aida-mcp  # launches stdio server manually (once installed via uv tool)
+```
+
+Commit helper (enforces footer policy and 70-char subject limit):
+
+```bash
+aida-mcp commit \
+  --type chore \
+  --scope aida \
+  --title "add commit helper command" \
+  --body "Enforce risk footer ordering and metadata trailers." \
+  --jira DX-123 \
+  --risk nonprod
+```
+
+Prefer running the command directly in this shape; do not probe with `aida-mcp commit --help` unless troubleshooting.
+
+Optional metadata in the footer block:
+- `--co-authored-by "Name <email>"` (repeatable)
+- `--ai-share actor=percent` (repeatable, must sum to 100)
+- `--ai-share-auto <actor>` for deterministic `<actor>=100` without guessing (policy-gated)
+- multiline body support:
+  - `--body-file /path/to/body.txt`
+  - `--body-stdin` (pipe or heredoc)
+  - `--body-line ...` (repeatable)
+
+`aida-mcp commit` policy values (for example title length, allowed `risk:` values, and optional required trailers) are configurable via `.aida/git_policy.yaml`.
+`Co-authored-by` is explicit-only: pass `--co-authored-by` when available; if omitted, no co-author trailer is added.
+
+Validation CLI shortcuts still live in the repo root:
+
+```bash
+make format-fix lint-fix
+make types
+make test
+make validate       # fast default (format/lint/types + unit tests)
+make validate-all   # includes integration tests (slow)
+```
+
+---
+
+## Troubleshooting & Workflow Guides
+
+Rather than duplicating multiple pages of instructions here, refer to:
+- [CONTRIBUTING.md](CONTRIBUTING.md): environment prep, Cursor integration, node/uv requirements, manual overrides, and how to add new tools/rules.
+- [docs/validation-tools.md](docs/validation-tools.md): deep dive into each tool’s steps, parameters, and best practices.
+- Developer onboarding docs under `docs/developer/` for broader GoodData setup.
+
+---
+
+## FAQ
+
+**Why a single `validate` tool?**
+Repo-owned routing (`.aida/*`) lets `aida-mcp` live in a separate repo while still executing GoodData-specific validations (often via external wrappers) with streaming progress.
+
+**Can I add custom output processors as external commands?**
+Not in unified validate today. Processors are built-in only; for custom behavior, either emit JSON consumed by `external_json` or add a new reusable built-in processor in `packages/aida-mcp`.
+
+**Can I run Docker/OpenAPI without rewriting commands?**
+Yes—when the repo’s `.aida/validation_policy.yaml` routes those steps. Add dedicated pipelines/commands for `docker`/`openapi` when needed.
+
+**What happens if the MCP client disconnects during validation?**
+The server gracefully handles invalid or closed MCP contexts. Progress updates are silently skipped if the context becomes unavailable, preventing server crashes. Validation continues to completion and returns results normally.
+
+**What if Python tests fail with "duplicate file name metadata.proto"?**
+The Python validator automatically detects this common issue (stale protobuf artifacts in `.venv`) and runs `make ultra-clean` + `make dev` to rebuild the environment, then retries the test step. This recovery is transparent and only triggers when needed.
+
+**How do I extend validation routing?**
+Update `.aida/change_domains.yaml` + `.aida/validation_policy.yaml`, and add commands in `.aida/validation_registry.yaml` as needed.
+
+---
+
+## Upgrading / breaking changes
+
+When AIDA source changes in a way that affects the MCP server executable, the installed tool set, or the MCP tool schema, you must **reinstall/refresh the MCP server setup** in your client.
+
+- **Action**: rerun `cd packages/aida-mcp && make install`, then restart/reload your client.
+- **Why**: clients cache the MCP server command + environment from MCP config files. Reinstall ensures the client points at the current `aida-mcp` executable and tool definitions.
+
+---
+
+## Repository setup
+
+This repository is AIDA-ready (repo-owned `.aida/` and repo-local MCP stubs are committed), so you can install the tool and start using it immediately.
+
+---
+
+Happy validating! Let the assistants run the noisy commands so you can stay focused on the code. For contributions, open an issue or follow the checklist in [CONTRIBUTING.md](CONTRIBUTING.md).

aida_mcp-0.1.2.dev1/pyproject.toml

@@ -0,0 +1,95 @@
+[project]
+name = "aida-mcp"
+version = "0.1.2.dev1"
+description = "AIDA MCP server - Developer actions (lint, test, typecheck) for monorepos"
+authors = [{name = "GoodData Corporation", email = "support@gooddata.com"}]
+readme = "README.md"
+requires-python = ">=3.12,<3.14"
+dependencies = [
+    "mcp>=1.25.0",
+    "pydantic>=2.10.6",
+    "structlog>=25.3.0",
+    "junitparser>=3.1.2",
+    "orjson>=3.11.5",
+    "pyyaml>=6.0.1",
+    "httpx>=0.28.0",
+    # Embeddings for semantic rule retrieval
+    "sentence-transformers>=3.0.0",
+    # dependency for sentence-transformers
+    "torch>=2.9.0",
+    "numpy>=1.26.0",
+    "langchain-text-splitters>=0.2.0",
+]
+
+[project.scripts]
+aida-mcp = "aida_mcp.server.cli:main"
+
+[dependency-groups]
+dev = [
+    "ruff>=0.11.5",
+    "ty>=0.0.14",
+    "pytest>=8.3.5",
+    "pytest-asyncio>=0.25.3",
+    "pytest-cov>=6.0.0",
+    "coverage>=7.6.0",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build]
+include = ["src/aida_mcp/**/*"]
+ignore-vcs = true
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/aida_mcp"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py312"
+exclude = [
+    ".git",
+    ".venv",
+    "venv",
+    "__pycache__",
+    "build",
+    "dist",
+]
+
+[tool.ruff.lint]
+select = [
+    "E",
+    "F",
+    "I",
+    "N",
+    "UP",
+    "W",
+    "C4",
+    "PIE",
+    "SIM",
+]
+ignore = [
+    "E501",  # Line too long (handled by formatter)
+]
+
+[tool.ruff.lint.isort]
+force-wrap-aliases = true
+combine-as-imports = true
+
+[tool.pytest.ini_options]
+asyncio_default_fixture_loop_scope = "function"
+testpaths = ["tests"]
+pythonpath = ["src"]
+
+[tool.ty.environment]
+# Keep aligned with `gooddata-python-sdk` configuration.
+extra-paths = ["src"]
+
+[[tool.uv.index]]
+name = "pytorch"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true
+
+[tool.uv.sources]
+torch = { index = "pytorch" }

aida_mcp-0.1.2.dev1/src/aida_mcp/__init__.py

@@ -0,0 +1 @@
+"""AIDA (AI Developer Assistant) - Developer action tools for GoodData monorepo."""

aida_mcp-0.1.2.dev1/src/aida_mcp/embedded_rules/__init__.py

@@ -0,0 +1,6 @@
+"""Embedded rules shipped with the aida-mcp package.
+
+This package is intentionally designed to make `get_rules` portable across repos:
+- `general/`: reusable, repo-agnostic rules (always available)
+- `vendor/`: vendor-specific rules (default-on, configurable via env toggle)
+"""

aida_mcp-0.1.2.dev1/src/aida_mcp/embedded_rules/general/__init__.py

@@ -0,0 +1 @@
+"""General embedded rules (repo-agnostic)."""

aida_mcp-0.1.2.dev1/src/aida_mcp/embedded_rules/general/github/commit-and-push.mdc

@@ -0,0 +1,49 @@
+---
+description: Commit and push workflow - require aida-mcp commit and enforce tool co-author identity
+alwaysApply: false
+---
+
+# Commit and push workflow
+
+## Preferred_commit_command
+- `aida-mcp commit` is mandatory for commit creation.
+- Do not use raw `git commit` in normal assistant flow.
+- Use the direct command template instead of probing with `aida-mcp commit --help`.
+- Canonical command shape:
+  - `aida-mcp commit --type <type> --scope <scope> --title "<title>" --body "<body>" --risk <value> --jira <ID>`
+  - optional metadata: `--co-authored-by "Name <email>"`, `--ai-share-auto <actor>`, `--ai-share actor=percent`
+
+## Commit_message_policy
+- Source of truth is repository commit policy.
+- `risk:` footer is mandatory.
+- `JIRA:` is optional and policy-driven.
+- Keep `risk:` as the last footer line.
+- On `pre_push`, validate commit messages in `upstream..HEAD` against policy (including subject length and footer rules).
+
+## AI_metadata_policy
+- Include AI contribution metadata via `aida-mcp commit`.
+- Use deterministic `--ai-share-auto <actor>` only when policy-enabled and authorship is clearly single-AI.
+- Use `--ai-share actor=percent` for known mixed contribution only.
+- If split is unknown, ask user instead of guessing.
+- `Co-authored-by` must identify the assistant/tool identity, never a human user.
+- Use canonical trailer name and casing: `Co-authored-by:`.
+- Pass `--co-authored-by "Name <email>"` explicitly with a tool identity. Approved examples:
+  - `Co-authored-by: Cursor GPT 5.3 Codex <cursoragent@cursor.com>`
+  - `Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>`
+
+## Fixups_and_history
+- Use `git commit --fixup=<sha>` for follow-up changes.
+- Autosquash only for unpublished history.
+- For published history, add a new commit instead of rewriting.
+
+## Non_interactive_git_execution
+- Never run interactive Git commands in assistant flow.
+- Always disable editor prompts for rebase/merge continuation:
+  - `GIT_EDITOR=true GIT_SEQUENCE_EDITOR=true GIT_MERGE_AUTOEDIT=no git rebase --continue`
+  - `GIT_EDITOR=true GIT_SEQUENCE_EDITOR=true GIT_MERGE_AUTOEDIT=no git cherry-pick --continue`
+- If a commit command may open an editor, pass message arguments explicitly or set:
+  - `GIT_EDITOR=true` for that command invocation.
+- Do not use interactive flags (for example `-i`) in automation paths.
+
+## Safe_push
+- Prefer `git push <remote> <branch> --force-with-lease` on feature branches.

aida_mcp-0.1.2.dev1/src/aida_mcp/embedded_rules/general/github/git-router.mdc

@@ -0,0 +1,21 @@
+---
+description: Git/GitHub router (entrypoint for commit, PR, and review workflows)
+alwaysApply: false
+required:
+  - github/commit-and-push.mdc
+---
+
+# Git & GitHub (router)
+
+## When_to_use
+- Query mentions: `git`, `github`, `commit`, `push`, `pull request`, `review comment`, `CI error`, `JIRA:`, `risk:`, `fixup`, `autosquash`
+
+## Owns
+- Entrypoint for Git/GitHub workflows.
+- Pull in detailed commit/PR/review guidance by topic.
+
+## How_to_query_get_rules
+- Prefer concrete queries:
+  - `commit then push with risk footer`
+  - `create pull request title body`
+  - `reply to review comments and CI failures`

aida_mcp-0.1.2.dev1/src/aida_mcp/embedded_rules/general/github/pull-requests.mdc

@@ -0,0 +1,23 @@
+---
+description: Pull request workflow - concise outcome-focused PRs with policy footer
+alwaysApply: false
+---
+
+# Pull requests
+
+## Title_and_body
+- Title: short, outcome-focused.
+- Body: what changed, why, and how to verify.
+
+## Workflow
+- Before PR creation/update, inspect branch state and included commits.
+- Ensure branch is pushed/up-to-date before creating/updating PR.
+
+## Required_footer
+- Include required footer lines per repository policy/rules.
+- Include required footer lines at the end of PR body.
+
+## Assistant_response_style
+- After creating/updating a PR, respond briefly.
+- Do not include PR URL by default.
+- Share URL only when user explicitly requests it.

aida_mcp-0.1.2.dev1/src/aida_mcp/embedded_rules/general/github/review-and-ci.mdc

@@ -0,0 +1,19 @@
+---
+description: PR review and CI workflow - reply/resolve review threads and fetch CI failures
+alwaysApply: false
+---
+
+# Review comments and CI workflow
+
+## Review_threads
+- Reply inline using `github_comments(action="reply_to_review_comment", comment_url="...#discussion_r<ID>", body="...")`.
+- For code-change comments: implement -> validate -> commit -> push -> reply -> resolve.
+- For rationale-only comments: reply clearly, then resolve.
+
+## Resolve_threads
+- Resolve with `github_comments(action="resolve_review_thread", comment_url="...#discussion_r<ID>")`.
+- Do not resolve code-change threads before fixes are pushed.
+
+## CI_failures
+- Preferred: `github_ci_errors(pr_number=..., repo="owner/repo")`.
+- Retry with `include_log_tails=True` only if annotations are insufficient.