rails-ai-context 0.9.0 → 0.10.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 661adfd69ce52e181149673477e63271b1bb0d0e866f19b734e44054ba01e230
-  data.tar.gz: b9468609fa7b9579b49b3cc2fefff3a30c4ac3fdbaeac31643cf0a211f4e4a77
+  metadata.gz: 9c9dabd282aadc577e5a66416e23e27c72dc728328490e4ce1af213358c215f1
+  data.tar.gz: 291cfd489f7b0b639655e3d0cdb473b0859b68bfdc2ed7ca1199826ac234af0a
 SHA512:
-  metadata.gz: e3f09200ea197372810ce5526a9db0baa9f5c1f74072126c92b6a0318eaedb11bc0e2cb6b671d9b4de0813dd04e6cd86a97e9643f2952606fa2e8ae60ec9893b
-  data.tar.gz: 5fda7235d72d4ccca1b918b93ee6a57f02add14a911d7178a7120db195ab7e6d4e1846d234db88beb36d842ae838bf7394f4bf89361d5dd389e26824140aee1d
+  metadata.gz: 95fd8e8c760b88e74d321102d9a55fda265c8cc7fb1d7de1b15ac8a7bc09666d08ada3540c194a7e9c1f2b134c6913feee1583c788113ec6d368485a41259cbf
+  data.tar.gz: d6a09886b74f4ece17e4529cff42fe99cdd1c68c2a6e04413d979754d362f461cdd074c40fea576c98b4187c83306787eeb88f25ea4952ffa99d1dee9bec3a80

data/CHANGELOG.md

@@ -5,6 +5,17 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.10.0] - 2026-03-19
+
+### Added
+
+- **`rails_get_view` MCP tool** — get view template contents, partials, Stimulus references. Filter by controller or specific path. Supports summary/standard/full detail levels. Eliminates reading 490+ lines of view files per task. ([#7](https://github.com/crisnahine/rails-ai-context/issues/7))
+- **`rails_get_stimulus` MCP tool** — get Stimulus controller details (targets, values, actions, outlets, classes). Filter by controller name. Wraps existing StimulusIntrospector. ([#8](https://github.com/crisnahine/rails-ai-context/issues/8))
+- **`rails_get_controllers` `action` parameter** — returns actual action source code + applicable filters instead of the entire controller file. Saves ~1,400 tokens per call. ([#9](https://github.com/crisnahine/rails-ai-context/issues/9))
+- **`rails_get_test_info` enhanced** — now supports `detail` levels (summary/standard/full), `model` and `controller` params to find existing tests, fixture/factory names, test helper setup. ([#10](https://github.com/crisnahine/rails-ai-context/issues/10))
+- **ViewTemplateIntrospector** — new introspector that reads view file contents and extracts partial references and Stimulus data attributes.
+- **Stimulus in standard preset** — `:stimulus` introspector now included in the `:standard` preset (was `:full` only).
+
 ## [0.9.0] - 2026-03-19
 
 ### Added

data/CLAUDE.md

@@ -8,8 +8,8 @@ structure to AI assistants via the Model Context Protocol (MCP).
 - `lib/rails_ai_context.rb` — Main entry point, public API (Zeitwerk autoloaded)
 - `lib/rails_ai_context/configuration.rb` — User-facing config with presets (:standard, :full)
 - `lib/rails_ai_context/introspector.rb` — Orchestrates sub-introspectors
-- `lib/rails_ai_context/introspectors/` — 27 introspectors (schema, models, routes, jobs, gems, conventions, stimulus, database_stats, controllers, views, turbo, i18n, config, active_storage, action_text, auth, api, tests, rake_tasks, assets, devops, action_mailbox, migrations, seeds, middleware, engines, multi_database)
-- `lib/rails_ai_context/tools/` — 9 MCP tools using the official mcp SDK
+- `lib/rails_ai_context/introspectors/` — 28 introspectors (schema, models, routes, jobs, gems, conventions, stimulus, database_stats, controllers, views, view_templates, turbo, i18n, config, active_storage, action_text, auth, api, tests, rake_tasks, assets, devops, action_mailbox, migrations, seeds, middleware, engines, multi_database)
+- `lib/rails_ai_context/tools/` — 11 MCP tools using the official mcp SDK
 - `lib/rails_ai_context/serializers/` — Output formatters (claude, claude_rules, opencode, cursor_rules, windsurf, windsurf_rules, copilot, copilot_instructions, rules, markdown, JSON)
 - `lib/rails_ai_context/resources.rb` — MCP resources (static data AI clients read directly)
 - `lib/rails_ai_context/server.rb` — MCP server configuration (stdio + HTTP transports)
@@ -32,7 +32,7 @@ structure to AI assistants via the Model Context Protocol (MCP).
 6. **Diff-aware** — context regeneration skips unchanged files
 7. **Per-assistant serializers** — each AI tool gets tailored output format
 8. **Zeitwerk autoloading** — files loaded on-demand, not all upfront
-9. **Introspector presets** — `:standard` (9 core) default, `:full` (26) for power users
+9. **Introspector presets** — `:standard` (10 core) default, `:full` (28) for power users
 10. **MCP auto-discovery** — `.mcp.json` generated by install generator
 11. **Compact by default** — context files ≤150 lines, MCP tools use `detail` parameter (summary/standard/full)
 12. **Per-tool split rules** — `.claude/rules/`, `.cursor/rules/`, `.windsurf/rules/`, `.github/instructions/`
@@ -42,7 +42,7 @@ structure to AI assistants via the Model Context Protocol (MCP).
 ## Testing
 
 ```bash
-bundle exec rspec           # Run specs (408 examples)
+bundle exec rspec           # Run specs (412 examples)
 bundle exec rubocop         # Lint
 ```
 

data/CONTRIBUTING.md

@@ -18,8 +18,8 @@ The test suite uses [Combustion](https://github.com/pat/combustion) to boot a mi
 
 ```
 lib/rails_ai_context/
-├── introspectors/     # 27 introspectors (schema, models, routes, etc.)
-├── tools/             # 9 MCP tools with detail levels and pagination
+├── introspectors/     # 28 introspectors (schema, models, routes, etc.)
+├── tools/             # 11 MCP tools with detail levels and pagination
 ├── serializers/       # Per-assistant formatters (claude, opencode, cursor, windsurf, copilot, JSON)
 ├── server.rb          # MCP server setup (stdio + HTTP)
 ├── live_reload.rb     # MCP live reload (file watcher + cache invalidation)

data/README.md

@@ -7,15 +7,11 @@
 [![CI](https://github.com/crisnahine/rails-ai-context/actions/workflows/ci.yml/badge.svg)](https://github.com/crisnahine/rails-ai-context/actions)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 
-![Token Comparison](https://raw.githubusercontent.com/crisnahine/rails-ai-context/main/docs/token-comparison.jpeg)
-
 *Built by a Rails dev who got tired of burning tokens explaining his app to AI assistants every single session.*
 
-![Demo](https://raw.githubusercontent.com/crisnahine/rails-ai-context/main/demo.gif)
-
 ---
 
-## Why?
+## The Problem
 
 You open Claude Code, Cursor, or Copilot and ask: *"Add a draft status to posts with a scheduled publish date."*
 
@@ -23,9 +19,24 @@ The AI doesn't know your schema, your Devise setup, your Sidekiq jobs, or that `
 
 **rails-ai-context fixes this.** It auto-introspects your entire Rails app and feeds everything to your AI assistant — schema, models, routes, controllers, jobs, gems, auth, API, tests, config, and conventions — through the [Model Context Protocol (MCP)](https://modelcontextprotocol.io).
 
-**No configuration. No manual tool definitions. Just `bundle add` and go.**
+---
 
-> **[Full Guide](docs/GUIDE.md)** — complete documentation with every command, parameter, and configuration option.
+## Proof: 35% Token Savings (Real Benchmark)
+
+We ran the same feature task — *"Add status and date range filters to the Cooks index page"* — across 4 scenarios in parallel on a real Rails app:
+
+| Scenario | MCP Tools | CLAUDE.md | Tokens Used | Savings |
+|----------|-----------|-----------|-------------|---------|
+| **MCP + CLAUDE.md** | Yes | Yes | **25,884** | **35% saved** |
+| MCP only | Yes | No | 27,822 | 31% saved |
+| CLAUDE.md only | No | Yes | 32,699 | 19% saved |
+| Zero (nothing) | No | No | 40,129 | baseline |
+
+All 4 produced the same working feature. The only difference was how many tokens were burned getting there.
+
+https://github.com/user-attachments/assets/171f52ae-bd30-43f6-a44f-bcfdda7fc139
+
+MCP tools give the AI structured, filtered access to your codebase instead of reading entire files. On this small 5-model app, that saved 35%. **On larger projects, the savings compound significantly.**
 
 ---
 
@@ -41,11 +52,64 @@ That's it. Three commands. Your AI assistant now understands your entire Rails a
 
 The install generator creates `.mcp.json` for auto-discovery — Claude Code and Cursor detect it automatically. No manual MCP config needed.
 
+> **[Full Guide](docs/GUIDE.md)** — complete documentation with every command, parameter, and configuration option.
+
+---
+
+## How It Saves Tokens
+
+![Token Comparison](https://raw.githubusercontent.com/crisnahine/rails-ai-context/main/docs/token-comparison.jpeg)
+
+- Compact context files load ≤150 lines instead of thousands
+- MCP tools return `detail:"summary"` first (~55 tokens for schema overview), then drill into specifics
+- Specific lookups (`table:`, `model:`, `controller:`) return only what's needed
+- Pagination prevents dumping hundreds of tables/routes at once
+- Split rule files only activate in relevant directories
+
+---
+
+## 11 Live MCP Tools
+
+The gem exposes **11 read-only tools** via MCP that AI clients call on-demand:
+
+| Tool | What it returns |
+|------|----------------|
+| `rails_get_schema` | Tables, columns, indexes, foreign keys |
+| `rails_get_model_details` | Associations, validations, scopes, enums, callbacks |
+| `rails_get_routes` | HTTP verbs, paths, controller actions |
+| `rails_get_controllers` | Actions, filters, strong params, concerns |
+| `rails_get_config` | Cache, session, timezone, middleware, initializers |
+| `rails_get_test_info` | Test framework, factories, CI config, coverage |
+| `rails_get_gems` | Notable gems categorized by function |
+| `rails_get_conventions` | Architecture patterns, directory structure |
+| `rails_search_code` | Ripgrep-powered regex search across the codebase |
+| `rails_get_view` | View templates, partials, Stimulus references |
+| `rails_get_stimulus` | Stimulus controllers — targets, values, actions, outlets |
+
+### Smart Detail Levels
+
+Schema, routes, models, and controllers tools support a `detail` parameter — critical for large apps:
+
+| Level | Returns | Default limit |
+|-------|---------|---------------|
+| `summary` | Names + counts | 50 |
+| `standard` | Names + key details *(default)* | 15 |
+| `full` | Everything (indexes, FKs, constraints) | 5 |
+
+```ruby
+rails_get_schema(detail: "summary")           # → all tables with column counts
+rails_get_schema(table: "users")              # → full detail for one table
+rails_get_routes(controller: "users")         # → routes for one controller
+rails_get_model_details(model: "User")        # → associations, validations, scopes
+```
+
+A safety net (`max_tool_response_chars`, default 120K) truncates oversized responses with hints to use filters.
+
 ---
 
 ## What Gets Generated
 
-`rails ai:context` generates **20 files** tailored to each AI assistant:
+`rails ai:context` generates context files tailored to each AI assistant:
 
 ```
 your-rails-app/
@@ -53,9 +117,9 @@ your-rails-app/
 ├── 🟣 Claude Code
 │   ├── CLAUDE.md                                         ≤150 lines (compact)
 │   └── .claude/rules/
+│       ├── rails-context.md                              app overview
 │       ├── rails-schema.md                               table listing
 │       ├── rails-models.md                               model listing
-│       ├── rails-context.md                               app overview
 │       └── rails-mcp-tools.md                            full tool reference
 │
 ├── 🟢 Cursor
@@ -87,9 +151,7 @@ your-rails-app/
 └── .mcp.json                                             MCP auto-discovery
 ```
 
-Each file respects the AI tool's format and size limits. **Commit these files** — your entire team gets smarter AI assistance.
-
-> Use `rails ai:context:full` to dump everything into the files (good for small apps <30 models).
+Root files (CLAUDE.md, AGENTS.md, etc.) use **section markers** — your custom content outside the markers is preserved on re-generation. Set `config.generate_root_files = false` to only generate split rules.
 
 ---
 
@@ -98,13 +160,13 @@ Each file respects the AI tool's format and size limits. **Commit these files**
 | Category | What's introspected |
 |----------|-------------------|
 | **Database** | Every table, column, index, foreign key, and migration |
-| **Models** | Associations, validations, scopes, enums, callbacks, concerns, macros (`has_secure_password`, `encrypts`, `normalizes`, etc.) |
+| **Models** | Associations, validations, scopes, enums, callbacks, concerns, macros |
 | **Routing** | Every route with HTTP verbs, paths, controller actions, API namespaces |
 | **Controllers** | Actions, filters, strong params, concerns, API controllers |
 | **Views** | Layouts, templates, partials, helpers, template engines, view components |
-| **Frontend** | Stimulus controllers (targets, values, actions, outlets), Turbo Frames/Streams, model broadcasts |
+| **Frontend** | Stimulus controllers (targets, values, actions, outlets), Turbo Frames/Streams |
 | **Background** | ActiveJob classes, mailers, Action Cable channels |
-| **Gems** | 70+ notable gems categorized (Devise = auth, Sidekiq = jobs, Pundit = authorization, etc.) |
+| **Gems** | 70+ notable gems categorized (Devise = auth, Sidekiq = jobs, Pundit = authorization) |
 | **Auth** | Devise modules, Pundit policies, CanCanCan, has_secure_password, CORS, CSP |
 | **API** | Serializers, GraphQL, versioning, rate limiting, API-only mode |
 | **Testing** | Framework, factories/fixtures, CI config, coverage, system tests |
@@ -112,76 +174,7 @@ Each file respects the AI tool's format and size limits. **Commit these files**
 | **DevOps** | Puma, Procfile, Docker, deployment tools, asset pipeline |
 | **Architecture** | Service objects, STI, polymorphism, state machines, multi-tenancy, engines |
 
-27 introspectors total. The `:standard` preset runs 9 core ones by default; use `:full` for all 27.
-
----
-
-## MCP Tools
-
-The gem exposes **9 live tools** via MCP that AI clients call on-demand:
-
-| Tool | What it returns |
-|------|----------------|
-| `rails_get_schema` | Tables, columns, indexes, foreign keys |
-| `rails_get_model_details` | Associations, validations, scopes, enums, callbacks |
-| `rails_get_routes` | HTTP verbs, paths, controller actions |
-| `rails_get_controllers` | Actions, filters, strong params, concerns |
-| `rails_get_config` | Cache, session, timezone, middleware, initializers |
-| `rails_get_test_info` | Test framework, factories, CI config, coverage |
-| `rails_get_gems` | Notable gems categorized by function |
-| `rails_get_conventions` | Architecture patterns, directory structure |
-| `rails_search_code` | Ripgrep-powered regex search across the codebase |
-
-All tools are **read-only** — they never modify your application or database.
-
-### Smart Detail Levels
-
-Schema, routes, models, and controllers tools support a `detail` parameter — critical for large apps:
-
-| Level | Returns | Default limit |
-|-------|---------|---------------|
-| `summary` | Names + counts | 50 |
-| `standard` | Names + key details *(default)* | 15 |
-| `full` | Everything (indexes, FKs, constraints) | 5 |
-
-```ruby
-# Start broad
-rails_get_schema(detail: "summary")           # → all tables with column counts
-
-# Drill into specifics
-rails_get_schema(table: "users")              # → full detail for one table
-
-# Paginate large schemas
-rails_get_schema(detail: "summary", limit: 20, offset: 40)
-
-# Filter routes by controller
-rails_get_routes(controller: "users")
-
-# Get one model's full details
-rails_get_model_details(model: "User")
-```
-
-A safety net (`max_tool_response_chars`, default 120K) truncates oversized responses with hints to use filters.
-
-### Token Savings
-
-The summary-first approach dramatically reduces AI token consumption — especially for large apps:
-
-| Metric | Without gem | Full dump (v0.6) | Smart mode (v0.7+) |
-|--------|-------------|------------------|---------------------|
-| Context file | 0 tokens | ~15,000 tokens | ~1,500 tokens |
-| Schema lookup | manual copy-paste | ~45,000 tokens (all tables) | ~800 tokens (summary) |
-| Drill into 1 table | manual copy-paste | included above | ~400 tokens |
-| **2-call workflow** | **error-prone** | **~60,000 tokens** | **~2,700 tokens** |
-
-That's **~95% fewer tokens** for the same understanding. The AI gets a compact overview first, then only loads what it actually needs — you pay for precision, not bulk.
-
-**How it saves:**
-- Compact context files load ≤150 lines instead of thousands
-- `detail:"summary"` gives the AI the full landscape in ~800 tokens
-- Specific lookups (`table:`, `model:`, `controller:`) return only what's needed
-- Pagination prevents dumping hundreds of tables/routes at once
-- Split rule files only activate in relevant directories (e.g., model rules load only when editing `app/models/`)
+28 introspectors total. The `:standard` preset runs 10 core ones by default; use `:full` for 27 (`database_stats` is opt-in, PostgreSQL only).
 
 ---
 
@@ -235,7 +228,7 @@ end
 ```ruby
 # config/initializers/rails_ai_context.rb
 RailsAiContext.configure do |config|
-  # Presets: :standard (9 introspectors, default) or :full (all 27)
+  # Presets: :standard (10 introspectors, default) or :full (all 28)
   config.preset = :standard
 
   # Cherry-pick on top of a preset
@@ -269,7 +262,7 @@ end
 | Option | Default | Description |
 |--------|---------|-------------|
 | `preset` | `:standard` | Introspector preset (`:standard` or `:full`) |
-| `introspectors` | 9 core | Array of introspector symbols |
+| `introspectors` | 10 core | Array of introspector symbols |
 | `context_mode` | `:compact` | `:compact` (≤150 lines) or `:full` (dump everything) |
 | `claude_max_lines` | `150` | Max lines for CLAUDE.md in compact mode |
 | `max_tool_response_chars` | `120_000` | Safety cap for MCP tool responses |
@@ -286,29 +279,13 @@ end
 
 ---
 
-## Stack Compatibility
-
-Works with every Rails architecture — auto-detects what's relevant:
-
-| Setup | Coverage | Notes |
-|-------|----------|-------|
-| Rails full-stack (ERB + Hotwire) | 27/27 | All introspectors relevant |
-| Rails + Inertia.js (React/Vue) | ~22/27 | Views/Turbo partially useful, backend fully covered |
-| Rails API + React/Next.js SPA | ~20/27 | Schema, models, routes, API, auth, jobs — all covered |
-| Rails API + mobile app | ~20/27 | Same as SPA — backend introspection is identical |
-| Rails engine (mountable gem) | ~15/27 | Core introspectors (schema, models, routes, gems) work |
-
-Frontend introspectors (views, Turbo, Stimulus, assets) degrade gracefully — they report nothing when those features aren't present.
-
----
-
 ## Commands
 
 ### Rake tasks (recommended)
 
 | Command | Description |
 |---------|-------------|
-| `rails ai:context` | Generate all 20 context files (skips unchanged) |
+| `rails ai:context` | Generate all context files (skips unchanged) |
 | `rails ai:context:full` | Generate all files in full mode (dumps everything) |
 | `rails ai:context:claude` | Generate Claude Code files only |
 | `rails ai:context:opencode` | Generate OpenCode files only |
@@ -321,17 +298,9 @@ Frontend introspectors (views, Turbo, Stimulus, assets) degrade gracefully — t
 | `rails ai:watch` | Auto-regenerate context files on code changes |
 | `rails ai:inspect` | Print introspection summary to stdout |
 
-> **Context modes:**
-> ```bash
-> rails ai:context                              # compact (default) — all formats
-> rails ai:context:full                         # full dump — all formats
-> CONTEXT_MODE=full rails ai:context:claude     # full dump — Claude only
-> CONTEXT_MODE=full rails ai:context:cursor     # full dump — Cursor only
-> ```
-
 ### Standalone CLI
 
-The gem also ships a `rails-ai-context` executable — an alternative to rake tasks. Useful for `.mcp.json` configs or when you prefer a shorter command.
+The gem also ships a `rails-ai-context` executable — an alternative to rake tasks.
 
 | Command | Equivalent rake task |
 |---------|---------------------|
@@ -348,6 +317,22 @@ Run from your Rails app root. Use `rails-ai-context help` for all options.
 
 ---
 
+## Stack Compatibility
+
+Works with every Rails architecture — auto-detects what's relevant:
+
+| Setup | Coverage | Notes |
+|-------|----------|-------|
+| Rails full-stack (ERB + Hotwire) | 28/28 | All introspectors relevant |
+| Rails + Inertia.js (React/Vue) | ~22/27 | Views/Turbo partially useful, backend fully covered |
+| Rails API + React/Next.js SPA | ~20/27 | Schema, models, routes, API, auth, jobs — all covered |
+| Rails API + mobile app | ~20/27 | Same as SPA — backend introspection is identical |
+| Rails engine (mountable gem) | ~15/27 | Core introspectors (schema, models, routes, gems) work |
+
+Frontend introspectors (views, Turbo, Stimulus, assets) degrade gracefully — they report nothing when those features aren't present.
+
+---
+
 ## Works Without a Database
 
 The gem parses `db/schema.rb` as text when no database is connected. Works in CI, Docker build stages, and Claude Code sessions without a running DB.
@@ -377,7 +362,7 @@ The gem parses `db/schema.rb` as text when no database is connected. Works in CI
 ```bash
 git clone https://github.com/crisnahine/rails-ai-context.git
 cd rails-ai-context && bundle install
-bundle exec rspec       # 408 examples
+bundle exec rspec       # 412 examples
 bundle exec rubocop     # Lint
 ```
 

data/demo_script.sh

@@ -8,7 +8,7 @@ echo 'Fetching gem metadata from https://rubygems.org...'
 sleep 0.3
 echo 'Resolving dependencies...'
 sleep 0.3
-echo 'Installing rails-ai-context 0.9.0'
+echo 'Installing rails-ai-context 0.10.0'
 echo ''
 sleep 1
 

data/docs/GUIDE.md

@@ -246,7 +246,7 @@ rails ai:context:claude           # Use this instead (no quoting needed)
 
 ## MCP Tools — Full Reference
 
-All 9 tools are **read-only** and **idempotent** — they never modify your application or database.
+All 11 tools are **read-only** and **idempotent** — they never modify your application or database.
 
 ### rails_get_schema
 
@@ -568,7 +568,7 @@ RailsAiContext.configure do |config|
 end
 ```
 
-Both transports are **read-only** — they expose the same 9 tools and never modify your app.
+Both transports are **read-only** — they expose the same 11 tools and never modify your app.
 
 ---
 
@@ -579,7 +579,7 @@ Both transports are **read-only** — they expose the same 9 tools and never mod
 RailsAiContext.configure do |config|
   # --- Introspectors ---
 
-  # Presets: :standard (9 core, default) or :full (all 27)
+  # Presets: :standard (10 core, default) or :full (all 28)
   config.preset = :standard
 
   # Cherry-pick on top of a preset
@@ -636,7 +636,7 @@ end
 | Option | Type | Default | Description |
 |--------|------|---------|-------------|
 | `preset` | Symbol | `:standard` | Introspector preset (`:standard` or `:full`) |
-| `introspectors` | Array | 9 core symbols | Which introspectors to run |
+| `introspectors` | Array | 10 core symbols | Which introspectors to run |
 | `context_mode` | Symbol | `:compact` | `:compact` or `:full` |
 | `claude_max_lines` | Integer | `150` | Max lines for CLAUDE.md in compact mode |
 | `max_tool_response_chars` | Integer | `120_000` | Safety cap for MCP tool responses |
@@ -689,7 +689,7 @@ These run by default. Fast and cover core Rails structure.
 | `tests` | Test framework (rspec/minitest), factories/fixtures with locations and counts, system tests, CI config files, coverage tool, test helpers, VCR cassettes. |
 | `migrations` | Total count, schema version, pending migrations, recent migration history with detected actions (create_table, add_column, etc.), migration statistics. |
 
-### Full preset (27 introspectors)
+### Full preset (28 introspectors)
 
 Includes all standard introspectors plus:
 
@@ -812,7 +812,7 @@ OpenCode uses **per-directory lazy-loading**: when the agent reads a file, it wa
 
 | Setup | Coverage | Notes |
 |-------|----------|-------|
-| Rails full-stack (ERB + Hotwire) | 27/27 | All introspectors relevant |
+| Rails full-stack (ERB + Hotwire) | 28/28 | All introspectors relevant |
 | Rails + Inertia.js (React/Vue) | ~22/27 | Views/Turbo partially useful, backend fully covered |
 | Rails API + React/Next.js SPA | ~20/27 | Schema, models, routes, API, auth, jobs — all covered |
 | Rails API + mobile app | ~20/27 | Same as SPA — backend introspection is identical |

data/lib/rails_ai_context/configuration.rb

@@ -3,8 +3,8 @@
 module RailsAiContext
   class Configuration
     PRESETS = {
-      standard: %i[schema models routes jobs gems conventions controllers tests migrations],
-      full: %i[schema models routes jobs gems conventions stimulus controllers views turbo
+      standard: %i[schema models routes jobs gems conventions controllers tests migrations stimulus],
+      full: %i[schema models routes jobs gems conventions stimulus controllers views view_templates turbo
                i18n config active_storage action_text auth api tests rake_tasks assets
                devops action_mailbox migrations seeds middleware engines multi_database]
     }.freeze

data/lib/rails_ai_context/introspector.rb

@@ -57,6 +57,7 @@ module RailsAiContext
       when :database_stats then Introspectors::DatabaseStatsIntrospector.new(app)
       when :controllers    then Introspectors::ControllerIntrospector.new(app)
       when :views          then Introspectors::ViewIntrospector.new(app)
+      when :view_templates then Introspectors::ViewTemplateIntrospector.new(app)
       when :turbo          then Introspectors::TurboIntrospector.new(app)
       when :i18n           then Introspectors::I18nIntrospector.new(app)
       when :config         then Introspectors::ConfigIntrospector.new(app)

data/lib/rails_ai_context/introspectors/test_introspector.rb

@@ -15,9 +15,13 @@ module RailsAiContext
         {
           framework: detect_framework,
           factories: detect_factories,
+          factory_names: detect_factory_names,
           fixtures: detect_fixtures,
+          fixture_names: detect_fixture_names,
           system_tests: detect_system_tests,
           test_helpers: detect_test_helpers,
+          test_helper_setup: detect_test_helper_setup,
+          test_files: detect_test_files,
           vcr_cassettes: detect_vcr,
           ci_config: detect_ci,
           coverage: detect_coverage
@@ -97,6 +101,71 @@ module RailsAiContext
         end.flatten.sort
       end
 
+      def detect_factory_names
+        %w[spec/factories test/factories].each do |dir_rel|
+          dir = File.join(root, dir_rel)
+          next unless Dir.exist?(dir)
+
+          names = {}
+          Dir.glob(File.join(dir, "**/*.rb")).each do |path|
+            file = path.sub("#{root}/", "")
+            factories = File.read(path).scan(/factory\s+:(\w+)/).flatten
+            names[file] = factories if factories.any?
+          rescue
+            next
+          end
+          return names if names.any?
+        end
+        nil
+      end
+
+      def detect_fixture_names
+        %w[spec/fixtures test/fixtures].each do |dir_rel|
+          dir = File.join(root, dir_rel)
+          next unless Dir.exist?(dir)
+
+          names = {}
+          Dir.glob(File.join(dir, "**/*.yml")).each do |path|
+            file = File.basename(path, ".yml")
+            content = File.read(path) rescue next
+            # Top-level YAML keys are fixture names
+            keys = content.scan(/^(\w+):/).flatten
+            names[file] = keys if keys.any?
+          end
+          return names if names.any?
+        end
+        nil
+      end
+
+      def detect_test_helper_setup
+        helpers = %w[
+          spec/rails_helper.rb spec/spec_helper.rb
+          test/test_helper.rb
+        ]
+
+        setup = []
+        helpers.each do |rel|
+          path = File.join(root, rel)
+          next unless File.exist?(path)
+          content = File.read(path) rescue next
+          content.scan(/(?:config\.)?include\s+([\w:]+)/).each { |m| setup << m[0] }
+        end
+        setup.uniq
+      end
+
+      def detect_test_files
+        categories = {}
+        %w[models controllers requests system services integration features].each do |cat|
+          %w[spec test].each do |base|
+            dir = File.join(root, base, cat)
+            next unless Dir.exist?(dir)
+            count = Dir.glob(File.join(dir, "**/*.rb")).size
+            categories[cat] = { location: "#{base}/#{cat}", count: count } if count > 0
+          end
+        end
+        categories
+      end
+
       def detect_vcr
         dirs = [
           File.join(root, "spec/cassettes"),

data/lib/rails_ai_context/introspectors/view_template_introspector.rb

@@ -0,0 +1,81 @@
+# frozen_string_literal: true
+
+module RailsAiContext
+  module Introspectors
+    # Reads actual view template contents and extracts metadata:
+    # partial references, Stimulus controller usage, line counts.
+    # Separate from ViewIntrospector which focuses on structural discovery.
+    class ViewTemplateIntrospector
+      attr_reader :app
+
+      def initialize(app)
+        @app = app
+      end
+
+      def call
+        views_dir = File.join(app.root.to_s, "app", "views")
+        return { templates: {}, partials: {} } unless Dir.exist?(views_dir)
+
+        {
+          templates: scan_templates(views_dir),
+          partials: scan_partials(views_dir)
+        }
+      rescue => e
+        { error: e.message }
+      end
+
+      private
+
+      def scan_templates(views_dir)
+        templates = {}
+        Dir.glob(File.join(views_dir, "**", "*")).each do |path|
+          next if File.directory?(path)
+          next if File.basename(path).start_with?("_") # skip partials
+          next if path.include?("/layouts/")
+
+          relative = path.sub("#{views_dir}/", "")
+          content = File.read(path) rescue next
+          templates[relative] = {
+            lines: content.lines.count,
+            partials: extract_partial_refs(content),
+            stimulus: extract_stimulus_refs(content)
+          }
+        end
+        templates
+      end
+
+      def scan_partials(views_dir)
+        partials = {}
+        Dir.glob(File.join(views_dir, "**", "_*")).each do |path|
+          next if File.directory?(path)
+          relative = path.sub("#{views_dir}/", "")
+          lines = File.read(path).lines.count rescue 0
+          partials[relative] = { lines: lines }
+        end
+        partials
+      end
+
+      def extract_partial_refs(content)
+        refs = []
+        # render "partial_name" or render partial: "name"
+        content.scan(/render\s+(?:partial:\s*)?["']([^"']+)["']/).each { |m| refs << m[0] }
+        # render @collection
+        content.scan(/render\s+@(\w+)/).each { |m| refs << m[0] }
+        refs.uniq
+      end
+
+      def extract_stimulus_refs(content)
+        refs = []
+        # data-controller="name" or data-controller="name1 name2"
+        content.scan(/data-controller=["']([^"']+)["']/).each do |m|
+          m[0].split.each { |c| refs << c }
+        end
+        # data: { controller: "name" }
+        content.scan(/controller:\s*["']([^"']+)["']/).each do |m|
+          m[0].split.each { |c| refs << c }
+        end
+        refs.uniq
+      end
+    end
+  end
+end