rcrewai-rails 0.6.0 → 0.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 92b441696cd97a26aeca352027a7f8e4bdef639f34c452494599d51cb302b8b6
-  data.tar.gz: 00466757e89f9b12e46956dcdb38d67a40a938bb4a68d43e0292f79babfb6260
+  metadata.gz: 42ec86061d4e3a880fa4c985abc0f2ec55e6c7868b95c65d62f7d6de27324042
+  data.tar.gz: f73a244bd91a867dd450f94d5fe82ab02e968f62e0a82e311a8e9e736be99e46
 SHA512:
-  metadata.gz: ec0516a3dba432d2b1a6308f89981a65905e110a4ef543ed5a516476ab62f47c9ba86cdc538288e52512841c34e01f5c2e9146970420d6435144922c4e2926a7
-  data.tar.gz: 26fb59a9bed5be7db14f7520a57d037c23e46bf572adf7946c98cf6fbe2d67fd3dd682e85942c84b38d9807e612aeb575b104f4c411f1dcd450f3de2cb8ab7b1
+  metadata.gz: 366cdfeb973451b6144514e72bcfe07e3dc3269e0d9bf093f9c73949f2f660ce6f3b8f136cf3fb1af7e27f08b5210da4c785b0f3e6ac5a9827379f764733f151
+  data.tar.gz: b91f369cbdd7141f83e36a407742cc31af9ecff0a3563668ec50b91dd6689c82f2bd2cd40c3db6753ef693bd535e90782cf51cfa4afc2a074a2012683d20ed74

data/CHANGELOG.md

@@ -7,6 +7,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.6.1] - 2026-07-07
+
+### Fixed
+- Refresh the README for rcrewai 0.7: corrected the install-generator namespace
+  (`rcrewai:rails:install`) and removed a broken crew-level `memory_enabled`
+  example (that DSL method no longer exists — memory is agent-level). Added a
+  "rcrewai 0.7 capabilities" section documenting the new agent/task/crew/
+  knowledge/flow configuration. Docs only.
+
 ## [0.6.0] - 2026-07-07
 
 Tracks rcrewai 0.7.0: adds the `:consensual` crew process and agent-level
@@ -114,7 +123,8 @@ existing agents, tasks, and crews build unchanged.
 ### Changed
 - Rename generators from `rcrew_a_i` to `rcrewai` namespacing.
 
-[Unreleased]: https://github.com/gkosmo/rcrewai-rails/compare/v0.6.0...HEAD
+[Unreleased]: https://github.com/gkosmo/rcrewai-rails/compare/v0.6.1...HEAD
+[0.6.1]: https://github.com/gkosmo/rcrewai-rails/compare/v0.6.0...v0.6.1
 [0.6.0]: https://github.com/gkosmo/rcrewai-rails/compare/v0.5.1...v0.6.0
 [0.5.1]: https://github.com/gkosmo/rcrewai-rails/compare/v0.5.0...v0.5.1
 [0.5.0]: https://github.com/gkosmo/rcrewai-rails/compare/v0.4.0...v0.5.0

data/README.md

@@ -10,6 +10,11 @@ Rails engine for integrating [RcrewAI](https://github.com/gkosmo/rcrewai-rails)
 - **Web UI**: Monitor and manage crews through a built-in interface
 - **Rails-Specific Tools**: Pre-built tools for ActiveRecord, ActionMailer, Rails cache, and more
 - **Configuration**: Flexible configuration through Rails initializers
+- **Full rcrewai 0.7 feature coverage** (see [rcrewai 0.7 capabilities](#rcrewai-07-capabilities)):
+  - Agent config: reasoning, per-agent LLM, rate limiting, context-window trimming, cognitive memory
+  - Task output: structured output schemas, guardrails, file output, multimodal attachments
+  - Crew: `before_kickoff`/`after_kickoff` hooks, planning, the `consensual` process, batch execution
+  - Knowledge (RAG) sources and Flow persistence
 
 ## Installation
 
@@ -28,7 +33,7 @@ $ bundle install
 Run the installation generator:
 
 ```bash
-$ rails generate rcrew_a_i:rails:install
+$ rails generate rcrewai:rails:install
 $ rails db:migrate
 ```
 
@@ -103,8 +108,7 @@ class ResearchCrew
   
   crew_name "research_team"
   crew_description "AI-powered research team"
-  process_type :sequential
-  memory_enabled true
+  process_type :sequential # :sequential, :hierarchical, or :consensual
   
   def setup_agents
     @researcher = create_agent("researcher",
@@ -187,6 +191,101 @@ crew.execute_sync(inputs)
 CrewExecutionJob.set(wait: 5.minutes).perform_later(crew, inputs)
 ```
 
+## rcrewai 0.7 capabilities
+
+This engine tracks [rcrewai](https://github.com/gkosmo/rcrewAI) `~> 0.7`. The
+following capabilities are configured through columns on the persisted models and
+forwarded to the core objects at build time. All are **off/absent by default**, so
+existing records are unaffected — set only what you need.
+
+### Agent configuration (`RcrewAI::Rails::Agent`)
+
+| Column | Effect |
+|---|---|
+| `max_rpm` | Rate-limit the agent's LLM calls (requests per minute) |
+| `reasoning` / `max_reasoning_attempts` | Run a planning/reasoning pass before answering |
+| `respect_context_window` | Trim history to fit the model's context window |
+| `llm_config` (JSON) | Per-agent LLM override, e.g. `{ "provider": "anthropic", "model": "claude-sonnet-5" }` |
+| `memory_enabled` + `memory_scope` + `memory_short_term_limit` | Enable cognitive memory (see below) |
+
+```ruby
+agent = crew.agents.create!(
+  name: "researcher", role: "Researcher", goal: "Find facts",
+  reasoning: true,
+  max_rpm: 30,
+  llm_config: { provider: "anthropic", model: "claude-sonnet-5" },
+  memory_enabled: true, memory_scope: "research", memory_short_term_limit: 20
+)
+```
+
+**Agent memory** (rcrewai 0.6+): set `memory_enabled: true` to turn on cognitive
+memory. `memory_scope` isolates an agent's memories; `memory_short_term_limit`
+caps recent-execution recall. The embedder and store are objects, so configure
+them once in the initializer:
+
+```ruby
+RcrewAI::Rails.configure do |config|
+  config.default_memory_embedder = RCrewAI::Knowledge::Embedder.new
+  config.default_memory_store     = RCrewAI::Memory::SqliteStore.new(path: "db/rcrewai_memory.sqlite3")
+end
+```
+
+### Task output processing (`RcrewAI::Rails::Task`)
+
+| Column | Effect |
+|---|---|
+| `output_schema` (JSON) | Validate/coerce the result against a JSON schema (structured output) |
+| `guardrail_class` + `guardrail_method_name` + `guardrail_max_retries` | Validate/transform output, retrying on failure |
+| `output_file` + `create_directory` + `markdown` | Write the result to disk |
+| `attachments` (JSON) | Multimodal image inputs, e.g. `[{ "type": "image", "url": "https://…" }]` |
+
+A guardrail is resolved from a host class: `guardrail_class` names a class whose
+`guardrail_method_name` accepts the output and returns `[ok, value_or_error]`.
+
+### Crew orchestration (`RcrewAI::Rails::Crew`)
+
+| Column | Effect |
+|---|---|
+| `process_type` | `"sequential"`, `"hierarchical"`, or `"consensual"` |
+| `consensus_agents` | Number of proposers for the `consensual` process (default 3) |
+| `planning` / `planning_llm` | Run a planner pass before execution |
+| `before_kickoff_class`/`_method`, `after_kickoff_class`/`_method` | Lifecycle hooks resolved from host classes |
+
+**Batch execution** (rcrewai `kickoff_for_each` parity) runs the crew once per
+input set, one `Execution` per input grouped by a shared `batch_id`:
+
+```ruby
+result = crew.execute_batch_sync([{ topic: "a" }, { topic: "b" }])
+crew.batch_executions(result[:batch_id]) # the runs, in order
+crew.execute_batch_async(inputs_list)     # enqueue N jobs, returns the batch_id
+```
+
+### Knowledge (RAG)
+
+Attach sources to an agent (role-specific) or a crew (shared with all its agents):
+
+```ruby
+agent.knowledge_sources.create!(source_type: "url",    value: "https://example.com/doc")
+crew.knowledge_sources.create!(source_type: "string", value: "Reference text…")
+# source_type: "string" | "file" | "pdf" | "csv" | "url"
+```
+
+Active sources are embedded lazily at execution. See the memory initializer above
+for embedder configuration.
+
+### Flows
+
+Define Flow subclasses in your app (Ruby); the engine persists their state and
+runs. Pass `RcrewAI::Rails::ActiveRecordStateStore` so flows resume from the DB,
+and use `FlowRun.execute` to track a kickoff:
+
+```ruby
+run = RcrewAI::Rails::FlowRun.execute(MyFlow, inputs: { topic: "ruby" })
+run.status     # "completed" / "failed"
+run.result     # the final flow state
+RcrewAI::Rails::FlowState.find_by(state_id: run.state_id) # the persisted state
+```
+
 ## Database Models
 
 The gem provides these ActiveRecord models:
@@ -196,6 +295,9 @@ The gem provides these ActiveRecord models:
 - `RcrewAI::Rails::Task` - Task definitions
 - `RcrewAI::Rails::Execution` - Execution history
 - `RcrewAI::Rails::ExecutionLog` - Detailed execution logs
+- `RcrewAI::Rails::KnowledgeSource` - Knowledge (RAG) sources, owned by an agent or a crew
+- `RcrewAI::Rails::FlowState` - Persisted rcrewai Flow state (resume flows across restarts)
+- `RcrewAI::Rails::FlowRun` - Flow-run tracking (status, inputs, result, timing)
 
 ## API Endpoints
 

data/lib/rcrewai/rails/version.rb

@@ -1,6 +1,6 @@
 module RcrewAI
   module Rails
-    VERSION = "0.6.0"
+    VERSION = "0.6.1"
     Version = VERSION
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rcrewai-rails
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.6.1
 platform: ruby
 authors:
 - gkosmo