agentic-devtools 0.2.40__tar.gz → 0.2.41__tar.gz

agentic_devtools-0.2.41/.github/agents/agdt.address-copilot-review.agent.md

@@ -0,0 +1,28 @@
+---
+description: "Address Copilot Review: Automatically address GitHub Copilot PR review comments by URL"
+---
+
+## User Input
+
+```text
+$ARGUMENTS
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+The expected input is a GitHub PR review comment URL of the form:
+`https://github.com/{owner}/{repo}/pull/{pr_number}#pullrequestreview-{review_id}`
+
+## Purpose
+
+Automate the full end-to-end workflow for addressing Copilot PR review comments:
+parse the review URL, fetch comments, triage, make code changes, reply, resolve
+threads, and re-request Copilot review.
+
+## Instructions
+
+Follow the detailed instructions in the corresponding prompt file
+(`.github/prompts/agdt.address-copilot-review.prompt.md`).
+
+## Next Step
+
+Task is complete.

{agentic_devtools-0.2.40 → agentic_devtools-0.2.41}/.github/agents/agdt.pull-request-review.file-review.agent.md

@@ -24,19 +24,22 @@ Review files and record approvals or requested changes.
 
 ## Prerequisites
 
-- **Required state**: `pull_request_id`, `file_review.file_path`
+- **Single-file commands** (actions 1–2): require `pull_request_id` and `file_review.file_path`
+- **Batch commands** (actions 3–5): require only `pull_request_id` — file paths are passed inline via `--file-paths` or `--reviews`
 - **Set state** (if not already set):
 
   ```bash
   agdt-set pull_request_id <value>
-  agdt-set file_review.file_path <value>
+  agdt-set file_review.file_path <value>   # only needed for single-file commands
   ```
 
 ## Actions
 
-1. Hand off to `@agdt.approve-file` to approve the file.
-
-2. Hand off to `@agdt.request-changes` to request changes.
+1. Hand off to `@agdt.approve-file` to approve a single file.
+2. Hand off to `@agdt.request-changes` to request changes on a single file.
+3. Use `agdt-approve-files` to batch-approve multiple files with a shared summary.
+4. Use `agdt-submit-reviews` to batch-submit reviews with defaults and per-item overrides.
+5. Use `agdt-request-changes-batch` to batch request-changes for multiple files.
 
 ## Expected Outcome
 

agentic_devtools-0.2.41/.github/prompts/agdt.address-copilot-review.prompt.md

@@ -0,0 +1,291 @@
+# Address Copilot PR Review Comments
+
+You are a senior software engineer addressing feedback from a GitHub Copilot pull request review.
+Follow this workflow systematically, completing each phase before proceeding to the next.
+
+---
+
+## Tooling Priority
+
+**Always prefer `agdt-*` commands** from agentic-devtools over raw alternatives:
+
+| Operation | Preferred (agdt-*) | Fallback (raw) |
+|-----------|-------------------|----------------|
+| Run tests | `agdt-test` + `agdt-task-wait` | _Do not run `pytest` directly; always use `agdt-test` commands._ |
+| Stage changes | `agdt-git-stage` | `git add` |
+| Commit & push | `agdt-git-save-work` | `git commit` + `git push` |
+| Force push | `agdt-git-force-push` | `git push --force-with-lease` |
+
+The `agdt-*` commands provide: centralized state tracking, consistent formatting, and background
+task management.
+
+---
+
+## Phase 1: Parse the Review URL
+
+Extract identifiers from the PR review URL provided as input.
+
+### Expected URL Format
+
+```text
+https://github.com/{owner}/{repo}/pull/{pr_number}#pullrequestreview-{review_id}
+```
+
+### Parse Out
+
+| Variable | Example |
+|----------|---------|
+| `owner` | `ayaiayorg` |
+| `repo` | `agentic-devtools` |
+| `pr_number` | `1009` |
+| `review_id` | `4019856282` |
+
+### Validation
+
+- Confirm the URL matches the expected pattern (note: the fragment uses
+  `pullrequestreview-` — singular, not plural).
+- If the URL is malformed or missing, **stop** and ask the user for a valid URL.
+
+---
+
+## Phase 2: Fetch Review Comments
+
+Retrieve all comments belonging to this specific review using the GitHub REST API.
+
+Reviews can exceed 100 comments, so you **must** handle pagination.
+
+### Command
+
+```bash
+# Use --paginate to ensure ALL pages of comments are fetched, not just the first 100
+gh api --paginate \
+  "repos/{owner}/{repo}/pulls/{pr_number}/reviews/{review_id}/comments" \
+  --jq '.[]'
+```
+
+### Relevant Fields per Comment
+
+| Field | Use |
+|-------|-----|
+| `id` | Database ID — needed for replying and mapping to GraphQL thread IDs |
+| `path` | File path the comment is on |
+| `line` | Line number (may be `null` for file-level comments) |
+| `body` | Full comment text (the reviewer's feedback) |
+| `diff_hunk` | The diff context the comment was placed on |
+
+### Output
+
+List each comment with its `id`, `path`, `line`, and a short excerpt of `body` so you can
+see what needs addressing.
+
+---
+
+## Phase 3: Triage Each Comment
+
+For each comment, read the `body` and `diff_hunk` to understand the reviewer's request.
+Also read the referenced file(s) in the working tree to understand the current state.
+
+### Classification
+
+| Category | Criteria | Action |
+|----------|----------|--------|
+| **Addressable** | The feedback is valid and a code/doc change will fix it | Make a change in the relevant file |
+| **Not addressable** | False positive, already correct, out of scope, or should not result in a change | Reply with a clear explanation |
+
+### Output
+
+Document a triage table:
+
+```markdown
+| Comment ID | File | Line | Category | Reason |
+|------------|------|------|----------|--------|
+| 12345 | src/foo.py | 42 | Addressable | Valid: missing null check |
+| 12346 | README.md | 10 | Not addressable | Already correct — GitHub diff rendering artifact |
+```
+
+---
+
+## Phase 4: Make Changes for Addressable Comments
+
+Edit files to address every comment classified as **addressable**. After **all** edits are
+complete, verify with tests, then commit and push once (not per-comment).
+
+### Verify Changes
+
+Run the test suite before committing to ensure edits don't break anything:
+
+```bash
+agdt-test
+agdt-task-wait
+```
+
+If tests fail, fix the issues before proceeding.
+
+### Commit & Push
+
+```bash
+agdt-set commit_message "<type>([#<issue>](https://github.com/{owner}/{repo}/issues/<issue>)): address copilot review feedback
+
+- <summary of changes>
+
+[#<issue>](https://github.com/{owner}/{repo}/issues/<issue>)"
+agdt-git-save-work
+agdt-task-wait
+```
+
+Choose the commit **type** based on the nature of the changes:
+
+| Type | When to use |
+|------|-------------|
+| `fix` | Bug fixes, incorrect behavior |
+| `refactor` | Code quality, readability, or structure improvements |
+| `style` | Formatting, naming, whitespace changes |
+| `docs` | Documentation-only changes |
+| `chore` | Maintenance tasks that don't affect production code |
+
+> If no GitHub issue is linked to the PR, do **not** use the PR number in the commit scope.
+> Ask the user which GitHub issue to use, or ask them to create/link an issue before committing.
+
+### Capture the Commit Hash
+
+```bash
+COMMIT_FULL=$(git log -1 --format="%H")
+COMMIT_SHORT=$(git log -1 --format="%h")
+```
+
+### Edge Case: No Addressable Comments
+
+If every comment was triaged as **not addressable**, skip the commit step and proceed
+directly to Phase 5 (replies only).
+
+---
+
+## Phase 5: Reply to Every Comment
+
+Send a reply to **each** comment from the review.
+
+### For Comments That WERE Addressed
+
+Use this reply template (with the actual commit hash from Phase 4):
+
+```text
+addressed in [{COMMIT_SHORT}](https://github.com/{owner}/{repo}/pull/{pr_number}/commits/{COMMIT_FULL})
+```
+
+### For Comments That Were NOT Addressed
+
+Reply with a clear, specific explanation of **why** the feedback was not applied. Examples:
+
+- "The tables already use standard single-pipe format (`| ... |`). The double-pipe
+  rendering may be a GitHub diff display artifact — the raw markdown is correct."
+- "This is already handled by the existing `validate()` call on line 45 — no change needed."
+- "This would be a breaking change outside the scope of this PR. Filed as
+  {owner}/{repo}#NNN to track separately."
+
+### Sending Replies via REST API
+
+For each comment, post a reply:
+
+```bash
+gh api "repos/{owner}/{repo}/pulls/{pr_number}/comments/{comment_id}/replies" \
+  -f body="<reply text>"
+```
+
+---
+
+## Phase 6: Resolve Review Threads
+
+After all replies are posted, resolve the corresponding discussion threads using GraphQL.
+
+### Step 1 — Map Comment IDs to Thread IDs
+
+PRs can have more than 100 review threads, so you **must** paginate using `pageInfo`
+and `endCursor`. Fetch pages until `hasNextPage` is `false`.
+
+```bash
+# First page (adjust "after" cursor for subsequent pages)
+gh api graphql -f query='query {
+  repository(owner: "{owner}", name: "{repo}") {
+    pullRequest(number: {pr_number}) {
+      reviewThreads(first: 100) {
+        pageInfo { hasNextPage endCursor }
+        nodes {
+          id
+          isResolved
+          comments(first: 1) {
+            nodes { databaseId }
+          }
+        }
+      }
+    }
+  }
+}'
+```
+
+If `pageInfo.hasNextPage` is `true`, fetch the next page by adding
+`after: "{endCursor}"` to the `reviewThreads` arguments. Repeat until all
+threads are collected.
+
+Filter the results to threads whose first comment `databaseId` is in the set of comment
+IDs from Phase 2, and that are **not already resolved**.
+
+### Step 2 — Resolve Each Thread
+
+```bash
+gh api graphql -f query='mutation {
+  resolveReviewThread(input: {threadId: "{thread_id}"}) {
+    thread { id isResolved }
+  }
+}'
+```
+
+---
+
+## Phase 7: Re-request Copilot Review
+
+Request a new review from the Copilot reviewer bot so it can verify the changes.
+
+```bash
+gh api "repos/{owner}/{repo}/pulls/{pr_number}/requested_reviewers" \
+  -X POST -f 'reviewers[]=copilot-pull-request-reviewer[bot]'
+```
+
+The Copilot reviewer's login is always `copilot-pull-request-reviewer[bot]`.
+
+---
+
+## Phase 8: Summary
+
+After completing all phases, present a summary to the user:
+
+```markdown
+## Copilot Review Comment Resolution Summary
+
+**PR:** {owner}/{repo}#{pr_number}
+**Review ID:** {review_id}
+**Total comments:** X
+
+### Results
+
+| Comment ID | File | Line | Category | Action Taken |
+|------------|------|------|----------|--------------|
+| 12345 | src/foo.py | 42 | Addressed | Fixed in {COMMIT_SHORT} |
+| 12346 | README.md | 10 | Not addressed | Already correct (explained) |
+
+### Status
+
+- [x] All comments replied to
+- [x] All threads resolved
+- [x] Copilot re-review requested
+- [x] Commit: {COMMIT_SHORT} (if changes were made)
+```
+
+---
+
+## Error Handling
+
+- **API rate limits**: If `gh api` returns a 403/429, wait and retry.
+- **Thread already resolved**: Skip silently — the GraphQL mutation is idempotent.
+- **Comment reply fails**: Log the error, continue with the remaining comments, and
+  report failures in the summary.
+- **No comments found**: If the review has zero comments, inform the user and stop.

{agentic_devtools-0.2.40 → agentic_devtools-0.2.41}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentic-devtools
-Version: 0.2.40
+Version: 0.2.41
 Summary: Agentic devtools integrate Jira, DevOps & more
 Author: ayaiayorg
 License-Expression: MIT

{agentic_devtools-0.2.40 → agentic_devtools-0.2.41}/agentic_devtools/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.2.40'
-__version_tuple__ = version_tuple = (0, 2, 40)
+__version__ = version = '0.2.41'
+__version_tuple__ = version_tuple = (0, 2, 41)
 
 __commit_id__ = commit_id = None

{agentic_devtools-0.2.40 → agentic_devtools-0.2.41}/agentic_devtools/cli/azure_devops/__init__.py

@@ -20,6 +20,7 @@ Example:
 # Config exports
 # Auth exports
 # Async command exports
+from .approve_files import approve_files_cli
 from .async_commands import (
     add_pull_request_comment_async,
     add_pull_request_comment_async_cli,
@@ -54,12 +55,16 @@ from .async_commands import (
     run_e2e_tests_fabric_async,
     run_e2e_tests_synapse_async,
     run_wb_patch_async,
-    submit_file_review_async,
+    submit_reviews_async,
+    submit_reviews_cli,
     update_pipeline_async,
     wait_for_run_async,
 )
 from .auth import get_auth_headers, get_pat
 
+# Batch review helpers
+from .batch_review_helpers import resolve_batch_reviews, validate_batch_reviews
+
 # Command exports
 from .commands import (
     add_pull_request_comment,
@@ -88,7 +93,7 @@ from .file_review_commands import (
     get_queue_status,
     request_changes,
     request_changes_with_suggestion,
-    submit_file_review,
+    submit_reviews,
 )
 
 # Helper exports
@@ -129,6 +134,9 @@ from .pr_summary_commands import (
 # Pull request details command exports
 from .pull_request_details_commands import get_pull_request_details
 
+# Request changes batch command
+from .request_changes_batch import request_changes_batch_cli
+
 # Review attribution exports
 from .review_attribution import (
     SHORT_HASH_LENGTH,
@@ -167,6 +175,7 @@ from .review_state import (
     get_review_state_file_path,
     load_review_state,
     normalize_file_path,
+    read_modify_write_review_state,
     save_review_state,
     update_file_status,
 )
@@ -274,18 +283,25 @@ __all__ = [
     # File review commands
     "approve_file",
     "get_queue_status",
-    "submit_file_review",
+    "submit_reviews",
     "request_changes",
     "request_changes_with_suggestion",
     # File review commands (async)
     "approve_file_async",
     "approve_file_async_cli",
-    "submit_file_review_async",
+    "submit_reviews_async",
+    "submit_reviews_cli",
     "request_changes_async",
     "request_changes_async_cli",
     "request_changes_with_suggestion_async",
     "request_changes_with_suggestion_async_cli",
     "mark_file_reviewed_async",
+    # Batch convenience commands
+    "approve_files_cli",
+    "request_changes_batch_cli",
+    # Submit reviews helpers
+    "resolve_batch_reviews",
+    "validate_batch_reviews",
     # Mark reviewed
     "mark_file_reviewed",
     "mark_file_reviewed_cli",
@@ -313,6 +329,7 @@ __all__ = [
     "get_review_state_file_path",
     "load_review_state",
     "save_review_state",
+    "read_modify_write_review_state",
     "get_file_entry",
     "get_folder_entry",
     "update_file_status",

agentic_devtools-0.2.41/agentic_devtools/cli/azure_devops/approve_files.py

@@ -0,0 +1,125 @@
+"""
+Batch approve multiple files with a shared summary.
+
+Provides ``approve_files_cli()`` — a convenience wrapper that constructs an
+``agdt-submit-reviews``-compatible payload with ``default_outcome="approve"``
+and delegates to ``submit_reviews_async()`` for durable background execution.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+
+from ...state import get_pull_request_id, is_dry_run
+from .batch_review_helpers import resolve_batch_reviews, validate_batch_reviews
+
+
+def approve_files_cli() -> None:
+    """CLI entry point for agdt-approve-files."""
+    parser = argparse.ArgumentParser(
+        prog="agdt-approve-files",
+        description="Batch approve multiple files with a shared summary",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Approve two files with the same summary
+  agdt-approve-files \\
+    --summary "Mechanical refactor only. LGTM." \\
+    --file-paths '["/src/a.ts","/src/b.ts"]'
+
+  # With explicit PR ID
+  agdt-approve-files \\
+    --pull-request-id 12345 \\
+    --summary "LGTM." \\
+    --file-paths '["/src/a.ts"]'
+        """,
+    )
+    parser.add_argument(
+        "--summary",
+        type=str,
+        required=True,
+        help="The approval summary applied to all files.",
+    )
+    parser.add_argument(
+        "--file-paths",
+        type=str,
+        required=True,
+        help='A JSON array string of file paths (e.g., \'["/src/a.ts","/src/b.ts"]\')',
+    )
+    parser.add_argument(
+        "--pull-request-id",
+        "-p",
+        type=int,
+        default=None,
+        help="Pull request ID (falls back to pull_request_id state)",
+    )
+    args = parser.parse_args()
+
+    # Parse --file-paths JSON
+    try:
+        file_paths = json.loads(args.file_paths)
+    except json.JSONDecodeError as e:
+        print(f"Error: --file-paths is not valid JSON: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if not isinstance(file_paths, list):
+        print("Error: --file-paths must be a JSON array.", file=sys.stderr)
+        sys.exit(1)
+
+    if not file_paths:
+        print("Error: --file-paths must contain at least one file path.", file=sys.stderr)
+        sys.exit(1)
+
+    for i, entry in enumerate(file_paths):
+        if not isinstance(entry, str) or not entry.strip():
+            print(f"Error: --file-paths item {i}: must be a non-empty string.", file=sys.stderr)
+            sys.exit(1)
+        file_paths[i] = entry.strip()
+
+    # Resolve pull_request_id
+    if args.pull_request_id is not None:
+        pr_id = args.pull_request_id
+    else:
+        pr_id = get_pull_request_id(required=False)
+        if pr_id is None:
+            print(
+                "Error: pull request ID is required. Provide --pull-request-id or set pull_request_id in state.",
+                file=sys.stderr,
+            )
+            sys.exit(1)
+
+    # Build payload
+    payload = {
+        "default_outcome": "approve",
+        "default_summary": args.summary,
+        "items": [{"file_path": p} for p in file_paths],
+    }
+
+    # Resolve + validate
+    resolved = resolve_batch_reviews(payload)
+    errors = validate_batch_reviews(resolved)
+    if errors:
+        for err in errors:
+            print(err, file=sys.stderr)
+        sys.exit(1)
+
+    # Dry-run check
+    if is_dry_run():
+        print(f"[DRY RUN] Would enqueue {len(resolved)} item(s):")
+        for item in resolved:
+            print(f"  {item['file_path']} — {item['outcome']}")
+        return
+
+    # Delegate to submit_reviews_async for durable background execution.
+    # This stores the payload in state and spawns a background subprocess
+    # via run_function_in_background, consistent with other agdt action commands.
+    from .async_commands import submit_reviews_async
+
+    submit_reviews_async(
+        reviews=json.dumps(resolved),
+        default_outcome="approve",
+        default_summary=args.summary,
+        pull_request_id=pr_id,
+    )