md-feedback

Advance workflow phase in strict sequence: scope -> root_cause -> implementation -> verification.

Apply an implementation action to a memo. Supports text_replace (requires occurrence or replaceAll when oldText has multiple matches; optional section-scoped propagation), file_patch (applies unified diff patch — snapshot saved first), and file_create (create a new file). Creates a snapshot before modification, records the implementation, and updates memo status to needs_review.

Approve a pending high-risk checkpoint. Grants one execution for the approved tool.

Apply multiple implementation operations in a single transaction. Parses the document once, applies all operations sequentially, then writes once. Each operation follows the same format as apply_memo.

Create a new review annotation on a markdown file. Finds the anchor text in the document and attaches a review memo. Auto-creates a quality gate and updates cursor.

Create a review checkpoint in an annotated markdown file. Records current annotation counts and reviewed sections.

Evaluate all gates in a markdown file against current memo statuses. Returns updated gate statuses without modifying the file.

Export review feedback in a format optimized for a specific AI coding tool. Targets: claude-code, cursor, codex, copilot, cline, windsurf, roo-code, gemini, antigravity, generic, handoff. Returns formatted markdown ready to save to the appropriate file.

Generate a structured handoff document from an annotated markdown file. Anti-compression format: explicit fields, numbers, lists only.

List all checkpoints in an annotated markdown file.

Parse an annotated markdown file and return v0.4.0 ReviewDocument metadata. By default bodyMd is omitted to reduce context size; set includeBody=true only when full body is required.

Get the implementation history and progress for a memo. Returns all MemoImpl records and progress entries from .md-feedback/progress.json. If memoId is omitted, returns all changes.

Return current runtime policy profile and memo-action routing rules.

Get current review session status: annotation counts, checkpoints, and reviewed sections. Summary-only — returns counts and metadata, not individual memos. Use list_annotations for memo details or get_document_structure for the full parse.

Return memo severity overrides and unresolved blocking memo IDs for the document.

Return current workflow phase and transition history for a document.

Link file artifacts (source files, configs, etc.) to a memo. Creates a MemoArtifact record in the document.

List all annotations (USER_MEMO comments) in a markdown file. Returns structured array with id, type, status, owner, text, and color. Lightweight — returns only memo data, no document body or sections. Use get_document_structure for the full parse.

List markdown files in the workspace. Optionally filter to only files that already contain annotations.

Parse an existing handoff document to resume a review session. Returns structured data for session continuity.

Create an approval checkpoint for a high-risk action before execution.

Add an AI response to a memo annotation. Inserts a REVIEW_RESPONSE block into the markdown file directly below the memo's anchor text. Automatically sets the memo status to "needs_review" for human approval.

Rollback the latest implementation for a memo. Reverses text_replace operations (swaps before/after), marks the impl as reverted, and sets the memo status back to open.

Set severity override for a memo. Defaults remain: fix=blocking, question/highlight=non_blocking.

Update the plan cursor position in a markdown file. The cursor tracks "where we are" in a plan. Only one cursor per document.

Update the progress of a memo with a status change and message. Writes progress to .md-feedback/progress.json and updates the memo status. Terminal statuses (done, failed) require human approval via VS Code.

Update the status of a memo annotation. Writes the change back to the markdown file. Returns the updated memo. Terminal statuses (answered, done, failed, wontfix) require human approval via VS Code.