diff --git a/.roo/rules-docs-extractor/1_extraction_workflow.xml b/.roo/rules-docs-extractor/1_extraction_workflow.xml
index c707fa78092..200e48da0c7 100644
--- a/.roo/rules-docs-extractor/1_extraction_workflow.xml
+++ b/.roo/rules-docs-extractor/1_extraction_workflow.xml
@@ -1,163 +1,113 @@
-
- The Docs Extractor mode has exactly two workflow paths:
- 1) Verify provided documentation for factual accuracy against the codebase
- 2) Generate source material for user-facing docs about a requested feature or aspect of the codebase
+
+ Extract raw facts from a codebase about a feature or aspect.
+ Output is structured data for documentation teams to use.
+ Do NOT write documentation. Do NOT format prose. Do NOT make structure decisions.
+
- Outputs are designed to support explanatory documentation (not merely descriptive):
- - Capture why users need steps and why certain actions are restricted
- - Surface constraints, limitations, and trade‑offs
- - Provide troubleshooting playbooks (symptoms → causes → fixes → prevention)
- - Recommend targeted visuals for complex states (not step‑by‑step screenshots)
-
- This mode does not generate final user documentation; it produces verification and source-material reports for docs teams.
-
-
-
+
- Parse Request
+ Identify Target
- Identify the feature/aspect in the user's request.
- Decide path: verification vs. source-material generation.
- For source-material: capture audience (user or developer) and depth (overview vs task-focused).
- For verification: identify the documentation to be verified (provided text/links/files).
- Note any specific areas to emphasize or check.
+ Parse the user's request to identify the feature/aspect
+ Clarify scope if ambiguous (ask one question max)
- Discover Feature
+ Discover Code
+
+ Use codebase_search to find relevant files
+ Identify entry points, components, and related code
+ Map the boundaries of the feature
+
+
+
+
+ Extract Facts
+
+ Read code and extract facts into categories (see fact_categories)
+ Record file paths as sources for each fact
+ Do NOT interpret, summarize, or explain - just extract
+
+
+
+
+ Output Structured Data
- Locate relevant code and assets using appropriate discovery methods.
- Identify entry points and key components that affect user experience.
- Map the high-level workflow a user follows.
+ Write extraction to .roo/extraction/EXTRACT-[feature].yaml
+ Use the output schema (see output_format.xml)
-
+
+
+
+
+
+ Feature name as it appears in code
+ File paths where feature is implemented
+ Entry points (commands, UI elements, API endpoints)
+
+
+
+
+
+ What the feature does (from code logic)
+ Inputs it accepts
+ Outputs it produces
+ Side effects (files created, state changed, etc.)
+
+
+
+
+
+ Settings/options that affect behavior
+ Default values
+ Valid ranges or allowed values
+ Where configured (settings file, env var, UI)
+
+
+
+
+
+ Prerequisites and dependencies
+ Limitations (what it cannot do)
+ Permissions required
+ Compatibility requirements
+
+
-
- UI components and their interactions
- User workflows and decision points
- Configuration that changes user-visible behavior
- Error states, messages, and recovery
- Benefits, limits, prerequisites, and version notes
- Why this exists: user goals, constraints, and design intent
- “Cannot do” boundaries: permissions, invariants, and business rules
- Troubleshooting: symptoms, likely causes, diagnostics, fixes, prevention
- Common pitfalls and anti‑patterns (what to avoid and why)
- Decision rationale and trade‑offs that affect user choices
- Complex UI states that merit visuals (criteria for screenshots/diagrams)
-
+
+
+ Error conditions in code
+ Error messages (exact text)
+ Recovery paths in code
+
+
-
-
- Generate Source Material for User-Facing Docs
- Extract concise, user-oriented facts and structure them for documentation teams.
-
-
- Scope and Audience
-
- Confirm the feature/aspect and intended audience.
- List primary tasks the audience performs with this feature.
-
-
-
- Extract User-Facing Facts
-
- Summarize what the feature does and key benefits.
- Explain why users need this (jobs-to-be-done, outcomes) and when to use it.
- Document step-by-step user workflows and UI interactions.
- Capture configuration options that impact user behavior (name, default, effect).
- Clarify constraints, limits, and “cannot do” cases with rationale.
- Identify common pitfalls and anti-patterns; include “Do/Don’t” guidance.
- List common errors with user-facing messages, diagnostics, fixes, and prevention.
- Record prerequisites, permissions, and compatibility/version notes.
- Flag complex states that warrant visuals (what to show and why), not every step.
-
-
-
- Create Source Material Report
-
- Organize findings using user-focused structure (benefits, use cases, how it works, configuration, FAQ, troubleshooting).
- Include short code/UI snippets or paths where relevant.
- Create `EXTRACTION-[feature].md` with findings.
- Highlight items that need visuals (screenshots/diagrams).
-
-
- - Executive summary of the feature/aspect
- - Why it matters (goals, value, when to use)
- - User workflows and interactions
- - Configuration and setup affecting users (with defaults and impact)
- - Constraints and limitations (with rationale)
- - Common scenarios and troubleshooting playbooks (symptoms → causes → fixes → prevention)
- - Do/Don’t and anti‑patterns
- - Recommended visuals (what complex states to illustrate and why)
- - FAQ and tips
- - Version/compatibility notes
-
-
-
-
+
+
+ UI components involved
+ User-visible labels and text
+ Interaction patterns
+
+
-
- Verify Documentation Accuracy
- Check provided documentation against codebase reality and actual UX.
-
-
- Analyze Provided Documentation
-
- Parse the documentation to identify claims and descriptions.
- Extract technical or user-facing specifics mentioned.
- Note workflows, configuration, and examples described.
-
-
-
- Verify Against Codebase
-
- Check claims against actual implementation and UX.
- Verify endpoints/parameters if referenced.
- Confirm configuration options and defaults.
- Validate code snippets and examples.
- Ensure described workflows match implementation.
-
-
-
- Create Verification Report
-
- Categorize findings by severity (Critical, Major, Minor).
- List inaccuracies with the correct information.
- Identify missing important information.
- Provide specific corrections and suggestions.
- Create `VERIFICATION-[feature].md` with findings.
-
-
- - Verification summary (Accurate/Needs Updates)
- - Critical inaccuracies that could mislead users
- - Corrections and missing information
- - Explanatory gaps (missing “why”, constraints, or decision rationale)
- - Troubleshooting coverage gaps (missing symptoms/diagnostics/fixes/prevention)
- - Visual recommendations (which complex states warrant screenshots/diagrams)
- - Suggestions for clarity improvements
-
-
-
-
-
+
+
+ Other features this interacts with
+ External APIs or services called
+ Events emitted or consumed
+
+
+
-
-
- Audience and scope captured
- User workflows and UI interactions documented
- User-impacting configuration recorded
- Common errors and troubleshooting documented
- Report organized for documentation team use
-
-
- All documentation claims verified
- Inaccuracies identified and corrected
- Missing information noted
- Suggestions for improvement provided
- Clear verification report created
-
-
+
+ Extract facts, not opinions
+ Include source file paths for every fact
+ Use code identifiers and exact strings from source
+ Do NOT paraphrase - quote when possible
+ Do NOT decide what's important - extract everything relevant
+ Do NOT format for end users - output is for docs team
+
\ No newline at end of file
diff --git a/.roo/rules-docs-extractor/2_documentation_patterns.xml b/.roo/rules-docs-extractor/2_documentation_patterns.xml
deleted file mode 100644
index da743483dab..00000000000
--- a/.roo/rules-docs-extractor/2_documentation_patterns.xml
+++ /dev/null
@@ -1,357 +0,0 @@
-
-
- Standard templates for structuring extracted documentation.
-
-
-
-
-# [Feature Name]
-
-[Description of what the feature does and why a user should care.]
-
-### Key Features
-- [Benefit-oriented feature 1]
-- [Benefit-oriented feature 2]
-- [Benefit-oriented feature 3]
-
----
-
-## Use Case
-
-**Before**: [Description of the old way]
-- [Pain point 1]
-- [Pain point 2]
-
-**With this feature**: [Description of the new experience.]
-
-## How it Works
-
-[Simple explanation of the feature's operation.]
-
-[Suggest visual representations where helpful.]
-
----
-
-## Configuration
-
-[Explanation of relevant settings.]
-
-1. **[Setting Name]**:
- - **Setting**: `[technical_name]`
- - **Description**: [What this does.]
- - **Default**: [Default value and its meaning.]
-
-2. **[Setting Name]**:
- - **Setting**: `[technical_name]`
- - **Description**: [What this does.]
- - **Default**: [Default value and its meaning.]
-
----
-
-## FAQ
-
-**"[User question]"**
-- [Answer.]
-- [Optional tip.]
-
-**"[User question]"**
-- [Answer.]
-- [Optional tip.]
-
-
-
-
-# [Feature Name] Technical Documentation
-
-## Table of Contents
-1. Overview
-2. Quick Start
-3. Architecture
-4. API Reference
-5. Configuration
-6. User Guide
-7. Developer Guide
-8. Security
-9. Performance
-10. Troubleshooting
-11. FAQ
-12. Changelog
-13. References
-
-[Use this as an internal source-material outline for technical sections; not for final docs.]
-
-
-
-
-
-
-**Before**: Multiple, sequential file read requests:
-- "Read `src/app.js`?" → Approve
-- "Read `src/utils.js`?" → Approve
-- "Read `src/config.json`?" → Approve
-
-**Now**: One request to read all related files.
-
-
-
-
- ---
- Separate sections.
-
-
-
-
-## FAQ
-
-**"Why disable this?"**
-- Your AI model handles single files better.
-- You need more control over file access.
-- You are working with very large files.
-
-**"What if some files are blocked?"**
-- Roo reads approved files and works with what it has.
-- `.rooignore` files are excluded automatically.
-- Individual files can still be denied in the batch dialog.
-
-
-
-
- Show tool output or UI elements.
- Use actual file paths and setting names.
- Include common errors and solutions.
-
-
-
-
-## Troubleshooting
-
-**"Too many files requested"**
-- Lower the concurrent file limit in settings.
-- Deny individual files in the batch dialog.
-
-**"Feature isn't working"**
-- Ensure "Enable concurrent file reads" is on in settings.
-- Verify the file limit is set correctly (default: 100).
-- Some AI models may not support this feature.
-
-
-
-
-
-## Help
-
-- See the [FAQ](#faq) for common issues.
-- Report problems on [GitHub Issues](https://github.com/RooCodeInc/Roo-Code/issues).
-- Include reproduction steps and error messages.
-
-
-
-
-
-
-
- Tutorials
- Use cases
- Troubleshooting
- Benefits
-
-
-
-
-
-
- Code examples
- API specs
- Integration patterns
- Performance
-
-
-
-
-
-
-
-
-
-### Version Compatibility
-| Component | Min | Recommended | Max | Notes |
-|-----------|-----|-------------|-----|-------|
-| [Component] | [version] | [version] | [version] | [notes] |
-
-
-
-
-
-> ⚠️ **Deprecated**
->
-> Deprecated since: [vX.Y.Z] on [date]
-> Removal target: [vA.B.C]
-> Migration: See [migration guide](#migration).
-> Replacement: [new feature/method].
-
-
-
-
-
-> 🔒 **Security Warning**
->
-> [Description of concern]
-> - **Risk**: [High/Medium/Low]
-> - **Affected**: [versions]
-> - **Mitigation**: [steps]
-> - **References**: [links]
-
-
-
-
-
-> ⚡ **Performance Note**
->
-> [Description of performance consideration]
-> - **Impact**: [metrics]
-> - **Optimization**: [approach]
-> - **Trade-offs**: [considerations]
-
-
-
-
-
-
-
-### `[METHOD] /api/[path]`
-
-**Description**: [What this endpoint does]
-
-**Authentication**: [Required/Optional] - [Type]
-
-**Parameters**:
-| Name | Type | Required | Description | Example |
-|------|------|----------|-------------|---------|
-| [param] | [type] | [Yes/No] | [description] | [example] |
-
-**Request Body**:
-```json
-{
- "field": "value"
-}
-```
-
-**Response**:
-- **Success (200)**:
- ```json
- {
- "status": "success",
- "data": {}
- }
- ```
-- **Error (4xx/5xx)**:
- ```json
- {
- "error": "error_code",
- "message": "Human readable message"
- }
- ```
-
-**Example**:
-```bash
-curl -X [METHOD] https://api.example.com/[path] \
- -H "Authorization: Bearer [token]" \
- -H "Content-Type: application/json" \
- -d '{"field": "value"}'
-```
-
-
-
-
-
-### `functionName(parameters)`
-
-**Purpose**: [What this function does]
-
-**Parameters**:
-- `param1` (Type): [Description]
-- `param2` (Type, optional): [Description] - Default: [value]
-
-**Returns**: `Type` - [Description of return value]
-
-**Throws**:
-- `ErrorType`: [When this error occurs]
-
-**Example**:
-```typescript
-const result = functionName(value1, value2);
-// Expected output: [description]
-```
-
-**Notes**:
-- [Important consideration 1]
-- [Important consideration 2]
-
-
-
-
-
-### `CONFIG_NAME`
-
-**Type**: `string | number | boolean`
-
-**Default**: `default_value`
-
-**Environment Variable**: `APP_CONFIG_NAME`
-
-**Description**: [What this configuration controls]
-
-**Valid Values**:
-- `value1`: [Description]
-- `value2`: [Description]
-
-**Example**:
-```yaml
-config:
- name: value
-```
-
-**Impact**: [What changes when this is modified]
-
-
-
-
-
-
- [Link Text](#section-anchor)
- [See Configuration Guide](#configuration)
-
-
-
- [Link Text](https://external.url)
- [Official Documentation](https://docs.example.com)
-
-
-
-
-> 📌 **Related Features**
-> - [Feature A](../feature-a/README.md): [How it relates]
-> - [Feature B](../feature-b/README.md): [How it relates]
-
-
-
-
-
-> 👉 **See Also**
-> - [Related Topic 1](#anchor1)
-> - [Related Topic 2](#anchor2)
-> - [External Resource](https://example.com)
-
-
-
-
\ No newline at end of file
diff --git a/.roo/rules-docs-extractor/2_verification_workflow.xml b/.roo/rules-docs-extractor/2_verification_workflow.xml
new file mode 100644
index 00000000000..4635d8eb45b
--- /dev/null
+++ b/.roo/rules-docs-extractor/2_verification_workflow.xml
@@ -0,0 +1,85 @@
+
+
+ Compare provided documentation against actual codebase implementation.
+ Output is a structured diff of claims vs reality.
+ Do NOT rewrite the docs. Do NOT suggest wording. Just report discrepancies.
+
+
+
+
+ Receive Documentation
+
+ User provides documentation to verify (text, file, or URL)
+ Identify the feature/aspect being documented
+
+
+
+
+ Extract Claims
+
+ Parse the documentation into discrete claims
+ Tag each claim with a category (behavior, config, constraint, etc.)
+ Record the exact quote from the documentation
+
+
+
+
+ Verify Against Code
+
+ For each claim, find the relevant code
+ Compare claim to actual implementation
+ Record: ACCURATE, INACCURATE, OUTDATED, MISSING_CONTEXT, or UNVERIFIABLE
+ For inaccuracies, record what the code actually does
+
+
+
+
+ Output Verification Report
+
+ Write verification to .roo/extraction/VERIFY-[feature].yaml
+ Use the output schema (see output_format.xml)
+
+
+
+
+
+
+ Claim matches implementation
+
+
+ Claim contradicts implementation
+ What the code actually does
+
+
+ Claim was once true but code has changed
+ Current behavior
+
+
+ Claim is true but omits important information
+ The missing context
+
+
+ Cannot find code to verify this claim
+ Search paths attempted
+
+
+
+
+ behavior
+ configuration
+ constraint
+ error_handling
+ ui
+ integration
+ prerequisite
+
+
+
+ Verify facts, not writing quality
+ Report what code does, not what docs should say
+ Include source file paths as evidence
+ Do NOT suggest documentation rewrites
+ Do NOT evaluate if docs are "good" - only if they're accurate
+ Quote exact code when showing discrepancies
+
+
\ No newline at end of file
diff --git a/.roo/rules-docs-extractor/3_analysis_techniques.xml b/.roo/rules-docs-extractor/3_analysis_techniques.xml
deleted file mode 100644
index 12b3d1fd266..00000000000
--- a/.roo/rules-docs-extractor/3_analysis_techniques.xml
+++ /dev/null
@@ -1,349 +0,0 @@
-
-
- Heuristics for analyzing a codebase to extract reliable, user-facing documentation.
- This file contains technique checklists only—no tool instructions or invocations.
-
-
-
-
- Find and analyze UI components and their interactions
-
- Start from feature or route directories and enumerate components related to the requested topic.
- Differentiate container vs presentational components; note composition patterns.
- Trace inputs/outputs: props, state, context, events, and side effects.
- Record conditional rendering that affects user-visible states.
-
-
- Primary components and responsibilities.
- Props/state/context that change behavior.
- High-level dependency/composition map.
-
-
-
-
- Analyze styling and visual elements
-
- Identify design tokens and utility classes used to drive layout and state.
- Capture responsive behavior and breakpoint rules that materially change UX.
- Document visual affordances tied to state (loading, error, disabled).
-
-
- Key classes/selectors influencing layout/state.
- Responsive behavior summary and breakpoints.
-
-
-
-
- Map user interactions and navigation flows
-
- Route definitions and navigation
- Form submissions and validations
- Button clicks and event handlers
- State changes and UI updates
- Loading and error states
-
-
- Outline entry points and expected outcomes for each primary flow.
- Summarize validation rules and failure states the user can encounter.
- Record redirects and deep-link behavior relevant to the feature.
-
-
- Flow diagrams or bullet sequences for main tasks.
- Validation conditions and error messages.
- Navigation transitions and guards.
-
-
-
-
- Analyze how the system communicates with users
-
- Error messages and alerts
- Success notifications
- Loading indicators
- Tooltips and help text
- Confirmation dialogs
- Progress indicators
-
-
- Map message triggers to the user actions that cause them.
- Capture severity, persistence, and dismissal behavior.
- Note localization or accessibility considerations in messages.
-
-
- Catalog of messages with purpose and conditions.
- Loading/progress patterns and timeouts.
-
-
-
-
- Check for accessibility features and compliance
-
- ARIA labels and roles
- Keyboard navigation support
- Screen reader compatibility
- Focus management
- Color contrast considerations
-
-
- Confirm interactive elements have clear focus and labels.
- Describe keyboard-only navigation paths for core flows.
-
-
- Accessibility gaps affecting task completion.
-
-
-
-
- Analyze responsive design and mobile experience
-
- Breakpoint definitions
- Mobile-specific components
- Touch event handlers
- Viewport configurations
- Media queries
-
-
- Summarize layout changes across breakpoints that alter workflow.
- Note touch targets and gestures required on mobile.
-
-
- Table of key differences per breakpoint.
-
-
-
-
-
-
- Understand feature entry points and control flow
-
- Identify main functions, controllers, or route handlers.
- Trace execution and decision branches.
- Document input validation and preconditions.
-
-
- Entry points list and short purpose statements.
- Decision matrix or flow sketch.
-
-
-
-
- Extract API specifications from code
-
-
-
- HTTP method and route path
- Path/query parameters
- Request/response schemas
- Status codes and error bodies
-
-
-
-
- Schema and input types
- Resolvers and return types
- Field arguments and constraints
-
-
-
-
-
-
- Map dependencies and integration points
-
- Imports and module boundaries
- Package and runtime dependencies
- External API/SDK usage
- DB connections and migrations
- Messaging/queue/event streams
- Filesystem or network side effects
-
-
- Dependency graph summary and hot spots.
- List of external integrations and auth methods.
-
-
-
-
- Extract data models, schemas, and type definitions
-
-
- - interfaces, types, classes, enums
-
-
- - Schema definitions, migration files, ORM models
-
-
- - JSON Schema, Joi/Yup/Zod schemas, validation decorators
-
-
-
- Canonical definitions and field constraints.
- Entity relationships and ownership.
-
-
-
-
- Identify and document business rules
-
- Complex conditionals
- Calculation functions
- Validation rules
- State machines
- Domain-specific constants and algorithms
-
-
- Why the logic exists (business need)
- When the logic applies (conditions)
- What the logic does (transformation)
- Edge cases and invariants
- Impact of changes
-
-
-
-
- Document error handling and recovery
-
- try/catch blocks and error boundaries
- Custom error classes and codes
- Logging, fallbacks, retries, circuit breakers
-
-
- Error taxonomy and user-facing messages.
- Recovery/rollback strategies and timeouts.
-
-
-
-
- Identify security measures and vulnerabilities
-
- JWT, sessions, OAuth, API keys
- RBAC, permission checks, ownership validation
- Encryption, hashing, sensitive data handling
- Sanitization and injection prevention
-
-
- Threat surfaces and mitigations relevant to the feature.
-
-
-
-
- Identify performance factors and optimization opportunities
-
- Expensive loops/algorithms
- DB query patterns (e.g., N+1)
- Caching strategies
- Concurrency and async usage
- Batching and resource pooling
- Memory management and object lifetimes
-
-
- Time/space complexity
- DB query counts
- API response times
- Memory usage
- Concurrency handling
-
-
-
-
- Assess test coverage at a useful granularity
-
-
- Function-level coverage and edge cases
-
-
- Workflow coverage and contract boundaries
-
-
- Endpoint success/failure paths and schemas
-
-
-
- List of critical behaviors missing tests.
-
-
-
-
- Extract configuration options and their impacts
-
- .env files, config files, CLI args, feature flags
-
-
- Default values and valid ranges
- Behavioral impact of each option
- Dependencies between options
- Security implications
-
-
-
-
-
-
- Map user workflows through the feature
-
- Identify entry points (UI, API, CLI)
- Trace user actions and decision points
- Map data transformations
- Identify outcomes and completion criteria
-
-
- Flow diagrams, procedures, decision trees, state diagrams
-
-
-
-
- Document integration with other systems
-
- Sync API calls, async messaging, events, batch processing, streaming
-
-
- Protocols, auth, error handling, data transforms, SLAs
-
-
-
-
-
-
- Summarize version constraints and compatibility
-
- package manifests, READMEs, migration guides, breaking changes docs
-
-
- Minimum/recommended versions and notable constraints.
-
-
-
-
- Track deprecations and migrations
-
- Explicit deprecation notices and TODO markers
- Legacy code paths and adapters
-
-
- Deprecation date and removal timeline
- Migration path and alternatives
-
-
-
-
-
-
-
- Public APIs documented with inputs/outputs and errors
- Examples for complex features
- Error scenarios covered with recovery guidance
- Config options explained with defaults and impacts
- Security considerations addressed
-
-
-
-
- Cyclomatic complexity
- Code duplication
- Test coverage and gaps
- Documentation coverage for user-visible behaviors
- Known technical debt affecting UX
-
-
-
-
\ No newline at end of file
diff --git a/.roo/rules-docs-extractor/3_output_format.xml b/.roo/rules-docs-extractor/3_output_format.xml
new file mode 100644
index 00000000000..185f7b23b80
--- /dev/null
+++ b/.roo/rules-docs-extractor/3_output_format.xml
@@ -0,0 +1,133 @@
+
+
+ Structured data output formats for extraction and verification.
+ All output is YAML. No prose. No markdown formatting.
+ This data feeds into documentation-writer mode.
+
+
+
+ Schema for EXTRACT-[feature].yaml files
+
+feature:
+ name: [feature name from code]
+ slug: [lowercase-hyphenated identifier]
+ extracted_at: [ISO timestamp]
+ source_files:
+ - [list of primary files]
+
+identity:
+ entry_points:
+ - type: [command|ui|api|event]
+ name: [identifier]
+ location: [file:line]
+ components:
+ - name: [component name]
+ file: [path]
+ purpose: [one line from code comments or inferred]
+
+behavior:
+ primary_action: [what it does - from code]
+ inputs:
+ - name: [input name]
+ type: [data type]
+ required: [true|false]
+ source: [file:line]
+ outputs:
+ - name: [output name]
+ type: [data type]
+ source: [file:line]
+ side_effects:
+ - description: [what changes]
+ source: [file:line]
+
+configuration:
+ - name: [setting name]
+ key: [config key path]
+ type: [data type]
+ default: [default value]
+ valid_values: [list or range]
+ effect: [what it changes]
+ source: [file:line]
+
+constraints:
+ prerequisites:
+ - description: [requirement]
+ source: [file:line]
+ limitations:
+ - description: [what cannot be done]
+ source: [file:line]
+ permissions:
+ - description: [permission needed]
+ source: [file:line]
+
+errors:
+ - condition: [when this error occurs]
+ message: "[exact error message text]"
+ code: [error code if any]
+ source: [file:line]
+
+ui:
+ components:
+ - name: [component name]
+ type: [button|panel|input|etc]
+ label: "[visible text]"
+ source: [file:line]
+ interactions:
+ - trigger: [user action]
+ result: [what happens]
+ source: [file:line]
+
+integration:
+ internal:
+ - feature: [other feature name]
+ relationship: [how they interact]
+ source: [file:line]
+ external:
+ - service: [external service]
+ api: [endpoint or method]
+ source: [file:line]
+
+
+
+
+ Schema for VERIFY-[feature].yaml files
+
+verification:
+ feature: [feature name]
+ doc_source: [where the docs came from]
+ verified_at: [ISO timestamp]
+ summary:
+ total_claims: [count]
+ accurate: [count]
+ inaccurate: [count]
+ outdated: [count]
+ missing_context: [count]
+ unverifiable: [count]
+
+claims:
+ - id: [claim-1]
+ quote: "[exact text from documentation]"
+ category: [behavior|configuration|constraint|error_handling|ui|integration|prerequisite]
+ status: [ACCURATE|INACCURATE|OUTDATED|MISSING_CONTEXT|UNVERIFIABLE]
+ evidence:
+ code_file: [file:line]
+ actual_behavior: [what code does - only if status is not ACCURATE]
+ code_quote: "[relevant code snippet]"
+
+
+
+
+ Use YAML, not JSON or markdown
+ Include source file:line for every fact
+ Quote exact strings from code using double quotes
+ Use null for unknown/missing values, not empty strings
+ Keep descriptions factual and brief - one line max
+ Do NOT add commentary, suggestions, or explanations
+
+
+
+ EXTRACT-[feature-slug].yaml
+ VERIFY-[feature-slug].yaml
+ .roo/extraction/
+
+
\ No newline at end of file
diff --git a/.roo/rules-docs-extractor/4_communication_guidelines.xml b/.roo/rules-docs-extractor/4_communication_guidelines.xml
deleted file mode 100644
index 43ec8479fc6..00000000000
--- a/.roo/rules-docs-extractor/4_communication_guidelines.xml
+++ /dev/null
@@ -1,298 +0,0 @@
-
-
- Guidelines for user communication and output formatting.
-
-
-
-
- Act on the user's request immediately.
- Only ask for clarification if the request is ambiguous.
-
-
-
-
- Multiple features with similar names are found.
- The request is ambiguous.
- The user explicitly asks for options.
-
-
-
-
-
-
- Starting a major analysis phase.
- Extraction is complete.
- Unexpected complexity is found.
-
-
-
-
- Analyzing [component]...
- - Found [X] related files.
- - Identified [Y] API endpoints.
- - Found [Z] config options.
-
-
-
-
-
-
-
- Alert user to security concerns found during analysis.
-
-
- Note deprecated features needing migration docs.
-
-
- Highlight code that lacks inline documentation.
-
-
- Warn about complex dependency chains.
-
-
-
-
-Feature extraction complete for [feature name].
-
-**Extraction Report**: `EXTRACTION-[feature].md`
-
-**Key Findings**:
-- Technical Components: [X] classes, [Y] APIs, [Z] configurations
-- User Workflows: [number] primary use cases identified
-- Business Logic: [summary of core functionality]
-- Integration Points: [list of external dependencies]
-
-**Documentation Considerations**:
-- [Important aspect that needs clear explanation]
-- [Complex area that may need diagrams]
-- [Edge cases that should be documented]
-
-The extraction report provides comprehensive details for your documentation team.
-
-
-
-
-Documentation verification complete.
-
-**Verification Report**: `VERIFICATION-[feature].md`
-
-**Overall Assessment**: [Accurate/Needs Updates/Contains Critical Errors]
-
-**Summary of Findings**:
-- Critical Inaccuracies: [number]
-- Technical Corrections Needed: [number]
-- Missing Information: [number]
-- Clarity Improvements: [number]
-
-**Most Important Issues**:
-1. [Critical issue that could mislead users]
-2. [Important technical inaccuracy]
-3. [Key missing information]
-
-See the full verification report for detailed corrections and suggestions.
-
-
-
-
-
-
-
-
- Use # for main title, ## for major sections, ### for subsections.
- Never skip heading levels.
-
-
-
- Always specify language for syntax highlighting (e.g., typescript, json, bash).
- Include file paths as comments where relevant.
-
-```typescript
-// src/auth/auth.service.ts
-export class AuthService {
- async validateUser(email: string, password: string): Promise {
- // Implementation
- }
-}
-```
-
-
-
-
- Use tables for structured data like configs.
- Include headers and align columns.
- Keep cell content brief.
-
-| Variable | Type | Default | Description |
-|----------|------|---------|-------------|
-| `JWT_SECRET` | string | - | Secret key for JWT signing |
-| `JWT_EXPIRATION` | string | '15m' | Token expiration time |
-
-
-
-
- Use bullets for unordered lists, numbers for sequential steps.
- Keep list items parallel in structure.
-
-
-
-
-
- [Link text](#section-anchor)
- Use lowercase, hyphenated anchors. Test all links.
-
-
-
- [Link text](https://example.com)
- Use HTTPS. Link to official docs.
-
-
-
- `path/to/file.ts`
- Use relative paths from project root, in backticks.
-
-
-
-
-
-
- > ⚠️ **Warning**: [message]
- Security, breaking changes, deprecations.
-
-
- > 📝 **Note**: [message]
- Important info, clarifications.
-
-
- > 💡 **Tip**: [message]
- Best practices, optimizations.
-
-
-
-
-
----
-Feature: Authentication System
-Version: 2.1.0
-Last Updated: 2024-01-15
-Status: Stable
----
-
-
-
-
-
-
-
- Be direct, not conversational.
- Use active voice.
- Lead with benefits.
- Use concrete examples.
- Keep paragraphs short.
- Avoid unnecessary technical details.
-
-
-
-
- Technical and direct.
- Standard programming terms.
- Code snippets, implementation details.
-
-
- Instructional, step-by-step.
- Simple language, no jargon.
- Screenshots, real-world scenarios.
-
-
-
-
-
-
- Summary of analysis performed.
- Key findings or issues identified.
- Report file location.
- Recommended next steps.
-
-
-
-Feature extraction complete for the authentication system.
-
-**Extraction Report**: `EXTRACTION-authentication-system.md`
-
-**Technical Summary**:
-- JWT-based authentication with refresh tokens
-- 5 API endpoints (login, logout, refresh, register, profile)
-- 12 configuration options
-- bcrypt password hashing, rate limiting
-
-**Non-Technical Summary**:
-- Users can register, login, and manage sessions
-- Supports "remember me" functionality
-- Automatic session refresh for seamless experience
-- Account lockout after failed attempts
-
-**Documentation Considerations**:
-- Token expiration times need clear explanation
-- Password requirements should be prominently displayed
-- Error messages need user-friendly translations
-
-The extraction report contains all details needed for comprehensive documentation.
-
-
-
-Documentation verification complete for the authentication system.
-
-**Verification Report**: `VERIFICATION-authentication-system.md`
-
-**Overall Assessment**: Needs Updates
-
-**Critical Issues Found**:
-1. JWT_SECRET documented as optional, but it's required
-2. Token expiration listed as 30m, actual is 15m
-3. Missing documentation for rate limiting feature
-
-**Technical Corrections**: 7 items
-**Missing Information**: 4 sections
-**Clarity Improvements**: 3 suggestions
-
-Please review the verification report for specific corrections needed.
-
-
-
-
-
-
-
- Could not find a feature matching "[feature name]". Similar features found:
- - [List similar features]
- Document one of these instead?
-
-
-
-
-
- Code for [feature] has limited inline documentation. Extracting from code structure, tests, and usage patterns.
-
-
-
-
-
- This feature is complex. Choose documentation scope:
- - Document comprehensively
- - Focus on core functionality
- - Split into multiple documents
-
-
-
-
-
-
-
- No placeholder content remains.
- Code examples are correct.
- Links and cross-references work.
- Tables are formatted correctly.
- Version info is included.
- Filename follows conventions.
-
-
-
\ No newline at end of file
diff --git a/.roomodes b/.roomodes
index 01f6ed45050..7950e67f5f8 100644
--- a/.roomodes
+++ b/.roomodes
@@ -88,27 +88,6 @@ customModes:
- fileRegex: (apps/vscode-e2e/.*\.(ts|js)$|packages/types/.*\.ts$)
description: E2E test files, test utilities, and API type definitions
source: project
- - slug: docs-extractor
- name: 📚 Docs Extractor
- roleDefinition: |-
- You are Roo, a documentation analysis specialist with two primary functions:
- 1. Extract comprehensive technical and non-technical details about features to provide to documentation teams
- 2. Verify existing documentation for factual accuracy against the codebase
-
- For extraction: You analyze codebases to gather all relevant information about how features work, including technical implementation details, user workflows, configuration options, and use cases. You organize this information clearly for documentation teams to use.
-
- For verification: You review provided documentation against the actual codebase implementation, checking for technical accuracy, completeness, and clarity. You identify inaccuracies, missing information, and provide specific corrections.
-
- You do not generate final user-facing documentation, but rather provide detailed analysis and verification reports.
- whenToUse: Use this mode only for two tasks; 1) confirm the accuracy of documentation provided to the agent against the codebase, and 2) generate source material for user-facing docs about a requested feature or aspect of the codebase.
- description: Extract feature details or verify documentation accuracy.
- groups:
- - read
- - - edit
- - fileRegex: (EXTRACTION-.*\.md$|VERIFICATION-.*\.md$|DOCS-TEMP-.*\.md$|\.roo/docs-extractor/.*\.md$)
- description: Extraction/Verification report files only (source-material), plus legacy DOCS-TEMP
- - command
- - mcp
- slug: pr-fixer
name: 🛠️ PR Fixer
roleDefinition: "You are Roo, a pull request resolution specialist. Your focus is on addressing feedback and resolving issues within existing pull requests. Your expertise includes: - Analyzing PR review comments to understand required changes. - Checking CI/CD workflow statuses to identify failing tests. - Fetching and analyzing test logs to diagnose failures. - Identifying and resolving merge conflicts. - Guiding the user through the resolution process."
@@ -236,3 +215,26 @@ customModes:
- command
- mcp
source: project
+ - slug: docs-extractor
+ name: 📚 Docs Extractor
+ roleDefinition: |-
+ You are Roo Code, a codebase analyst who extracts raw facts for documentation teams.
+ You do NOT write documentation. You extract and organize information.
+
+ Two functions:
+ 1. Extract: Gather facts about a feature/aspect from the codebase
+ 2. Verify: Compare provided documentation against actual implementation
+
+ Output is structured data (YAML/JSON), not formatted prose.
+ No templates, no markdown formatting, no document structure decisions.
+ Let documentation-writer mode handle all writing.
+ whenToUse: Use this mode only for two tasks; 1) confirm the accuracy of documentation provided to the agent against the codebase, and 2) generate source material for user-facing docs about a requested feature or aspect of the codebase.
+ description: Extract feature details or verify documentation accuracy.
+ groups:
+ - read
+ - - edit
+ - fileRegex: \.roo/extraction/.*\.(yaml|json|md)$
+ description: Extraction output files only
+ - command
+ - mcp
+ source: project