flock-core 0.5.0b60__tar.gz → 0.5.0b62__tar.gz

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/.pre-commit-config.yaml

@@ -79,7 +79,7 @@ repos:
         name: frontend build check
         entry: bash -c 'cd src/flock/frontend && npm run build'
         language: system
-        files: ^frontend/
+        files: ^src/flock/frontend/
         pass_filenames: false
         stages: [pre-push]  # Only on push, not on every commit
 

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/AGENTS.md

@@ -4,7 +4,7 @@
 
 This is Flock Flow, a production-grade blackboard-first AI agent orchestration framework. This guide gets you up to speed quickly on the current project state and development patterns.
 
-**Current Version:** 0.1.16
+**Current Version:** Backend: 0.5.0b62 • Frontend: 0.1.4
 **Architecture:** Hybrid Python/TypeScript with real-time dashboard
 **Package Manager:** UV (NOT pip!)
 **Status:** Production-ready with comprehensive monitoring
@@ -51,7 +51,7 @@ A blackboard architecture framework where specialized AI agents collaborate thro
 
 - **Python 3.10+** (we use modern async features)
 - **UV package manager** (faster than pip, handles virtual envs)
-- **Node.js 22+** (for dashboard frontend)
+- **Node.js 18+** (22+ recommended) for dashboard frontend
 - **OpenAI API key** (for running examples)
 
 ### Installation
@@ -66,7 +66,7 @@ poe install  # Equivalent to: uv sync --dev --all-groups --all-extras
 
 # Set up environment
 export OPENAI_API_KEY="sk-..."
-export DEFAULT_MODEL="openai/gpt-4o-mini"
+export DEFAULT_MODEL="openai/gpt-4.1"
 
 # Verify installation
 uv run python -c "from flock import Flock; print('✅ Ready!')"
@@ -75,14 +75,14 @@ uv run python -c "from flock import Flock; print('✅ Ready!')"
 ### Run Examples
 
 ```bash
-# Showcase examples (workshops & demos)
-uv run python examples/showcase/01_hello_flock.py
-uv run python examples/showcase/02_blog_review.py
-uv run python examples/showcase/04_dashboard.py
-
-# Feature examples (with assertions)
-uv run python examples/features/feedback_prevention.py
-uv run python examples/features/visibility/public_visibility.py
+# Core examples
+uv run python examples/01-the-declarative-way/01_declarative_pizza.py
+uv run python examples/01-the-declarative-way/02_input_and_output.py
+
+# Dashboard examples
+uv run python examples/03-the-dashboard/01_declarative_pizza.py
+uv run python examples/03-the-dashboard/02-dashboard-edge-cases.py
+uv run python examples/03-the-dashboard/03-scale-test-100-agents.py
 ```
 
 ---
@@ -91,45 +91,37 @@ uv run python examples/features/visibility/public_visibility.py
 
 For deep dives into specific topics, see:
 
-- **[Architecture Guide](docs/ai-agents/architecture.md)** - Core architecture, project structure, code style
-- **[Development Workflow](docs/ai-agents/development.md)** - Testing, quality standards, versioning, pre-commit hooks
-- **[Frontend Guide](docs/ai-agents/frontend.md)** - Dashboard usage, frontend development, React/TypeScript
-- **[Dependencies Guide](docs/ai-agents/dependencies.md)** - Package management, UV commands, adding dependencies
-- **[Common Tasks](docs/ai-agents/common-tasks.md)** - Adding agents/components, performance tips, security
+- **[Architecture & Blackboard](docs/guides/blackboard.md)** - Core pattern, structure, and behavior
+- **[Development Workflow](docs/about/contributing.md)** - Testing, quality, versioning, pre-commit
+- **[Frontend/Dashboard](docs/guides/dashboard.md)** - Dashboard usage and development
+- **[Configuration & Dependencies](docs/reference/configuration.md)** - Environment and setup
+- **[Patterns & Common Tasks](docs/guides/patterns.md)** - Recipes, performance, security
 
 ---
 
 ## 🚨 CRITICAL PATTERNS (Learn from Our Experience)
 
-### ⚡ invoke() vs run_until_idle() - The Double Execution Trap
+### ⚡ invoke() vs run_until_idle() - Execution Control (no double-run by default)
 
 **This pattern cost us hours of debugging - learn from our pain!**
 
-#### The Problem
-After API migration from `arun()` to `invoke()`, tests started executing component hooks **twice**:
-
-```python
-# Expected: ['A', 'B', 'C']
-# Actual: ['A', 'B', 'C', 'A', 'B', 'C']  # Double execution!
-```
+#### The Goal
+Choose between isolated agent execution and event-driven cascades.
 
-#### Root Cause Analysis
-`invoke()` method behavior depends on `publish_outputs` parameter:
+#### How it works
+`invoke()` behavior depends on `publish_outputs`:
 
 ```python
-# invoke() with default publish_outputs=True:
-await orchestrator.invoke(agent, input_artifact)
-await orchestrator.run_until_idle()  # ❌ Triggers SECOND execution!
-
-# invoke() with publish_outputs=False:
+# Isolated: execute agent only (no cascade)
 await orchestrator.invoke(agent, input_artifact, publish_outputs=False)
-# ✅ No double execution - just direct agent execution
+
+# Cascading: execute and publish outputs, then run downstream agents
+await orchestrator.invoke(agent, input_artifact, publish_outputs=True)
+await orchestrator.run_until_idle()  # processes downstream agents
 ```
 
-**Why this happens:**
-1. `invoke(..., publish_outputs=True)` executes agent AND publishes results to blackboard
-2. `run_until_idle()` processes published artifacts, triggering agent execution again
-3. Component hooks fire on BOTH executions → double execution
+Notes:
+- By default, agents have `prevent_self_trigger=True`, so an agent will not re-run on its own outputs when you call `run_until_idle()`. Downstream agents that subscribe to the output types will run.
 
 #### When to Use Which Pattern
 
@@ -161,12 +153,12 @@ assert len(output_artifacts) == 3
 #### Quick Reference
 
 | Scenario | invoke() call | run_until_idle() | Result |
-|----------|---------------|------------------|---------|
-| Unit test | `invoke(..., publish_outputs=False)` | No | ✅ Single execution |
-| Integration test | `invoke(..., publish_outputs=True)` | Yes | ✅ Cascade execution |
-| Bug we fixed | `invoke(..., publish_outputs=True)` | Yes | ❌ Double execution |
+|----------|---------------|------------------|--------|
+| Unit test | `invoke(..., publish_outputs=False)` | No | Single execution |
+| Integration test | `invoke(..., publish_outputs=True)` | Yes | Cascade to downstream agents |
+| Common mistake | `invoke(..., publish_outputs=True)` | Yes | Not a double-run; downstream agents run |
 
-**Rule of thumb:** Start with `publish_outputs=False` for tests, only enable publication if you specifically need cascade behavior.
+Rule of thumb: start with `publish_outputs=False` for unit tests; enable publication only when you want cascades.
 
 ---
 
@@ -297,7 +289,7 @@ The automated PyPI release pipeline checks if the version in `pyproject.toml` ha
 
 #### What to Bump
 
-**Backend version (REQUIRED for ALL changes):**
+**Backend version (REQUIRED for backend code changes):**
 ```toml
 # pyproject.toml
 [project]
@@ -317,14 +309,15 @@ version = "0.5.0b56"  # Increment this! e.g., "0.5.0b57"
 **✅ ALWAYS bump backend version for:**
 - Any Python code changes in `src/flock/`
 - Bug fixes, features, refactors
-- Documentation changes (increment patch)
-- Any commit that will be pushed to a branch
+- Commits that modify backend behavior
+
+Docs-only changes (in `docs/`, `README.md`) do not require a version bump.
 
 **✅ ALWAYS bump frontend version for:**
 - Dashboard UI changes
 - React/TypeScript component updates
 - CSS/styling changes
-- Any changes in `src/flock/frontend/src/`
+- Any changes in `src/flock/frontend/`
 
 #### Versioning Pattern
 
@@ -940,7 +933,7 @@ Always use the appropriate subdirectory:
 - **Source Code**: `/src/flock` - Production code only
 - **Documentation**: `/docs` - Documentation only
 - **Examples**: `/examples` - Example scripts only
-- **Frontend**: `/frontend/src` - React components and frontend code
+- **Frontend**: `src/flock/frontend/src` - React components and frontend code
 
 **Never create files in the root directory** - it should only contain configuration files like `pyproject.toml`, `README.md`, etc.
 

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: flock-core
-Version: 0.5.0b60
+Version: 0.5.0b62
 Summary: Add your description here
 Author-email: Andre Ratzenberger <andre.ratzenberger@whiteduck.de>
 License-File: LICENSE

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/docs/about/contributing.md

@@ -30,7 +30,7 @@ pre-commit install --hook-type pre-push
 
 # 4. Verify setup
 poe test
-cd frontend && npm test
+cd src/flock/frontend && npm test
 
 # You're ready to contribute! 🚀
 ```
@@ -41,7 +41,7 @@ cd frontend && npm test
 
 - **Python 3.10+** - Modern Python with async features
 - **UV Package Manager** - Fast, reliable dependency management (NOT pip!)
-- **Node.js 22+** - For frontend development
+- **Node.js 18+** (22+ recommended) - For frontend development
 - **Git** - Version control
 
 ### Recommended Tools
@@ -72,7 +72,7 @@ poe install
 
 # Or manually:
 uv sync --dev --all-groups --all-extras  # Install Python deps
-cd frontend && npm install                # Install frontend deps
+cd src/flock/frontend && npm install      # Install frontend deps
 ```
 
 ### 3. Set Up Environment Variables
@@ -83,7 +83,7 @@ cp .envtemplate .env
 
 # Edit .env and add your API keys
 export OPENAI_API_KEY="sk-..."
-export DEFAULT_MODEL="openai/gpt-4o-mini"
+export DEFAULT_MODEL="openai/gpt-4.1"
 ```
 
 ### 4. Install Pre-commit Hooks
@@ -134,7 +134,7 @@ poe version-check  # See what would be bumped
 poe version-minor  # Bump version
 
 # 7. Commit version bump
-git add pyproject.toml frontend/package.json
+   git add pyproject.toml src/flock/frontend/package.json
 git commit -m "chore: bump version to 0.2.0"
 
 # 8. Push (build checks run)
@@ -193,7 +193,7 @@ poe test-cov-fail
 poe test-critical
 
 # Frontend tests
-cd frontend && npm test
+cd src/flock/frontend && npm test
 
 # E2E tests
 poe test-e2e
@@ -219,7 +219,7 @@ from flock import Flock
 async def test_your_feature():
     """Test description following docstring conventions."""
     # Arrange
-    orchestrator = Flock("openai/gpt-4o-mini")
+    orchestrator = Flock("openai/gpt-4.1")
 
     # Act
     result = await orchestrator.do_something()
@@ -454,10 +454,10 @@ git diff package-lock.json
 
 ```bash
 # Terminal 1: Backend
-uv run python examples/showcase/04_dashboard.py
+uv run python examples/03-the-dashboard/01_declarative_pizza.py
 
 # Terminal 2: Frontend (if developing)
-cd frontend
+cd src/flock/frontend
 npm run dev
 
 # Dashboard opens at http://localhost:8000
@@ -497,7 +497,7 @@ poe docs
 **Solution**: Install dependencies
 ```bash
 poe install
-cd frontend && npm install
+cd src/flock/frontend && npm install
 ```
 
 ### UV not found

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/docs/examples/index.md

@@ -6,30 +6,24 @@ Learn by example! Explore working code samples demonstrating Flock's features an
 
 ## 🎯 Example Categories
 
-### Showcase Examples
+### Core Examples
 **Production-ready demonstrations of core features**
 
-Visit the [showcase examples](https://github.com/whiteducksoftware/flock/tree/main/examples/showcase) to see:
+Explore the numbered example folders in this repository:
 
-- **Hello Flock** - Minimal working example
-- **Blog Review** - Multi-agent content review workflow
-- **Pizza Ordering** - Type-driven agent coordination
-- **Dashboard Demo** - Real-time visualization
+- **01 — The Declarative Way** (`examples/01-the-declarative-way`) — minimal and focused
+- **02 — The Blackboard** (`examples/02-the-blackboard`) — architecture overview
+- **03 — The Dashboard** (`examples/03-the-dashboard`) — real-time monitoring
 
 ### Feature Examples
 **Focused examples for specific capabilities**
 
-Browse [feature examples](https://github.com/whiteducksoftware/flock/tree/main/examples/features) for:
-
-- **Feedback Prevention** - Avoid agent feedback loops
-- **Visibility Controls** - Public, private, and tenant-based access
-- **Custom Components** - Build your own plugins
-- **Custom Engines** - Beyond DSPy evaluation
+Feature-focused examples are integrated into the folders above (e.g., dashboard edge cases). Additional feature demos may be added over time.
 
 ### Dashboard Examples
 **Interactive dashboard demonstrations**
 
-Check out [dashboard examples](https://github.com/whiteducksoftware/flock/tree/main/examples/03-the-dashboard) to explore:
+Check out `examples/03-the-dashboard` to explore:
 
 - **Declarative Pizza** - Single-agent dashboard demo
 - **Edge Cases** - Multi-agent cascades and filtering
@@ -47,7 +41,7 @@ pip install "flock-core[all]"
 
 # Set your API key
 export OPENAI_API_KEY="sk-..."
-export DEFAULT_MODEL="openai/gpt-4o-mini"
+export DEFAULT_MODEL="openai/gpt-4.1"
 ```
 
 ### Run an Example
@@ -57,11 +51,11 @@ export DEFAULT_MODEL="openai/gpt-4o-mini"
 git clone https://github.com/whiteducksoftware/flock.git
 cd flock
 
-# Run a showcase example
-python examples/showcase/01_hello_flock.py
+# Run a minimal example
+python examples/01-the-declarative-way/01_declarative_pizza.py
 
 # Run with dashboard
-python examples/showcase/04_dashboard.py
+python examples/03-the-dashboard/01_declarative_pizza.py
 ```
 
 ---
@@ -84,7 +78,7 @@ class Greeting(BaseModel):
 class Response(BaseModel):
     message: str
 
-flock = Flock("openai/gpt-4o-mini")
+flock = Flock("openai/gpt-4.1")
 
 greeter = (
     flock.agent("greeter")
@@ -101,22 +95,15 @@ async def main():
 asyncio.run(main())
 ```
 
-**[View full example →](https://github.com/whiteducksoftware/flock/blob/main/examples/showcase/01_hello_flock.py)**
+Run it locally: `python examples/01-the-declarative-way/01_declarative_pizza.py`
 
 ---
 
-### 2. Blog Review (Multi-Agent)
-
-**What it demonstrates:** Agent cascades and type-driven coordination
-
-**Agents:**
-- `writer` - Consumes BlogIdea → Publishes BlogPost
-- `reviewer` - Consumes BlogPost → Publishes Review
-- `editor` - Consumes Review → Publishes FinalPost
+### 2. Dashboard Edge Cases
 
-**Key concept:** No explicit connections. Agents react to type availability.
+**What it demonstrates:** Agent cascades, filtering, and real-time updates
 
-**[View full example →](https://github.com/whiteducksoftware/flock/blob/main/examples/showcase/02_blog_review.py)**
+Run: `python examples/03-the-dashboard/02-dashboard-edge-cases.py`
 
 ---
 
@@ -137,29 +124,16 @@ await orchestrator.serve(
 )
 ```
 
-**[View full example →](https://github.com/whiteducksoftware/flock/blob/main/examples/showcase/04_dashboard.py)**
+Run: `python examples/03-the-dashboard/01_declarative_pizza.py`
 
 ---
 
 ### 4. Feedback Prevention
 
-**What it demonstrates:** Preventing agent feedback loops
-
-**Problem:** Agent A publishes type T, which triggers Agent B, which publishes type T, which triggers Agent A again...
-
-**Solution:** Use label-based visibility to break cycles
-
-```python
-await flock.publish(
-    artifact,
-    visibility=LabelVisibility(
-        allowed_agents=["agent_b"],
-        denied_agents=["agent_a"]  # Prevent feedback
-    )
-)
-```
+**What it demonstrates:** Preventing agent feedback loops using built-in safeguards
 
-**[View full example →](https://github.com/whiteducksoftware/flock/blob/main/examples/features/feedback_prevention.py)**
+- Default safeguard: `prevent_self_trigger=True` (agents won’t re-trigger on their own outputs)
+- Use label/tenant visibility for finer control (see Visibility guide)
 
 ---
 
@@ -174,7 +148,7 @@ Examples for:
 - **Label** - Fine-grained control
 - **Time** - Temporal constraints
 
-**[Browse visibility examples →](https://github.com/whiteducksoftware/flock/tree/main/examples/features/visibility)**
+See: Docs → User Guides → Visibility Controls
 
 ---
 
@@ -306,8 +280,8 @@ Have you built something cool with Flock? Share it!
 ## Related Documentation
 
 - **[Getting Started](../getting-started/index.md)** - Installation and quick start
-- **[User Guides](../guides/)** - Comprehensive guides
-- **[API Reference](../reference/)** - Complete API docs
+- **[User Guides](../guides/index.md)** - Comprehensive guides
+- **[API Reference](../reference/index.md)** - Complete API docs
 
 ---
 

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/docs/getting-started/index.md

@@ -49,7 +49,7 @@ New to Flock? Follow this recommended learning path:
 3. **[Core Concepts](concepts.md)** (15 minutes)
    Understand how Flock's blackboard architecture works
 
-4. **[User Guides](../guides/)** (ongoing)
+4. **[User Guides](../guides/index.md)** (ongoing)
    Dive deep into agents, blackboard patterns, and advanced features
 
 ---
@@ -107,7 +107,7 @@ Agents automatically execute when their input types appear on the blackboard. No
 
     Monitor and debug with OpenTelemetry and DuckDB.
 
-    [:octicons-arrow-right-24: Tracing Guide](../guides/tracing/)
+    [:octicons-arrow-right-24: Tracing Guide](../guides/tracing/tracing-quickstart.md)
 
 </div>
 

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/docs/getting-started/installation.md

@@ -95,7 +95,7 @@ export COHERE_API_KEY="..."
 ### Configure Default Model
 
 ```bash
-export DEFAULT_MODEL="openai/gpt-4o-mini"
+export DEFAULT_MODEL="openai/gpt-4.1"
 ```
 
 Flock uses [LiteLLM](https://docs.litellm.ai/docs/) for provider abstraction, supporting 100+ LLM providers.

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/docs/guides/components.md

@@ -201,7 +201,7 @@ from openai import AsyncOpenAI
 class ChatEngine(EngineComponent):
     """Simple chat-based LLM engine."""
 
-    def __init__(self, model: str = "gpt-4o-mini", temperature: float = 0.7):
+    def __init__(self, model: str = "openai/gpt-4.1", temperature: float = 0.7):
         super().__init__(name="chat_engine")
         self.client = AsyncOpenAI()
         self.model = model

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/docs/guides/index.md

@@ -184,4 +184,4 @@ Can't find what you're looking for?
 
 ---
 
-**Start with the basics** → [Getting Started](../getting-started/){ .md-button .md-button--primary }
+**Start with the basics** → [Getting Started](../getting-started/index.md){ .md-button .md-button--primary }

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/docs/guides/testing.md

@@ -57,7 +57,7 @@ class BugReport(BaseModel):
 async def test_bug_detector_finds_null_pointer():
     """Unit test: Bug detector identifies null pointer issues."""
     # Arrange
-    flock = Flock("openai/gpt-4o-mini", temperature=0)
+    flock = Flock("openai/gpt-4.1", temperature=0)
     bug_detector = flock.agent("bug_detector").consumes(CodeSnippet).publishes(BugReport)
 
     test_code = CodeSnippet(
@@ -93,7 +93,7 @@ Test multiple agents working together.
 async def test_code_review_workflow():
     """Integration test: Full code review with bug detection and security audit."""
     # Arrange
-    flock = Flock("openai/gpt-4o-mini", temperature=0)
+    flock = Flock("openai/gpt-4.1", temperature=0)
 
     @flock_type
     class CodeSubmission(BaseModel):
@@ -166,7 +166,7 @@ class StrictAnalysis(BaseModel):
 @pytest.mark.asyncio
 async def test_analysis_respects_constraints():
     """Contract test: Agent outputs respect field constraints."""
-    flock = Flock("openai/gpt-4o-mini", temperature=0)
+    flock = Flock("openai/gpt-4.1", temperature=0)
 
     @flock_type
     class Input(BaseModel):
@@ -212,7 +212,7 @@ Test agents with `where` clauses.
 @pytest.mark.asyncio
 async def test_conditional_consumption():
     """Test agent only processes high-severity items."""
-    flock = Flock("openai/gpt-4o-mini")
+    flock = Flock("openai/gpt-4.1")
 
     @flock_type
     class Alert(BaseModel):
@@ -254,7 +254,7 @@ from flock.subscription import BatchSpec
 @pytest.mark.asyncio
 async def test_batch_processing():
     """Test agent batches multiple events."""
-    flock = Flock("openai/gpt-4o-mini")
+    flock = Flock("openai/gpt-4.1")
 
     @flock_type
     class Event(BaseModel):
@@ -296,7 +296,7 @@ from flock.identity import AgentIdentity
 @pytest.mark.asyncio
 async def test_private_visibility_access_control():
     """Test private visibility restricts access."""
-    flock = Flock("openai/gpt-4o-mini")
+    flock = Flock("openai/gpt-4.1")
 
     @flock_type
     class SensitiveData(BaseModel):
@@ -376,7 +376,7 @@ async def test_agent_behavior():
 @pytest.mark.asyncio
 async def test_severity_routing(severity, expected_action):
     """Test different severity levels route correctly."""
-    flock = Flock("openai/gpt-4o-mini")
+    flock = Flock("openai/gpt-4.1")
 
     @flock_type
     class Alert(BaseModel):
@@ -401,7 +401,7 @@ async def test_severity_routing(severity, expected_action):
 @pytest.fixture
 async def code_review_flock():
     """Reusable flock setup for code review tests."""
-    flock = Flock("openai/gpt-4o-mini", temperature=0)
+    flock = Flock("openai/gpt-4.1", temperature=0)
 
     @flock_type
     class CodeSubmission(BaseModel):
@@ -444,7 +444,7 @@ async def test_agent_with_mocked_api(mock_call):
     """Test agent that calls external API."""
     mock_call.return_value = {"result": "mocked_response"}
 
-    flock = Flock("openai/gpt-4o-mini")
+    flock = Flock("openai/gpt-4.1")
     # ... rest of test
 ```
 
@@ -454,7 +454,7 @@ async def test_agent_with_mocked_api(mock_call):
 @pytest.mark.asyncio
 async def test_circuit_breaker_prevents_runaway():
     """Test circuit breaker stops infinite loops."""
-    flock = Flock("openai/gpt-4o-mini", max_agent_iterations=100)
+    flock = Flock("openai/gpt-4.1", max_agent_iterations=100)
 
     @flock_type
     class Trigger(BaseModel):
@@ -480,7 +480,7 @@ async def test_with_tracing():
     import os
     os.environ["FLOCK_AUTO_TRACE"] = "true"
 
-    flock = Flock("openai/gpt-4o-mini")
+    flock = Flock("openai/gpt-4.1")
 
     async with flock.traced_run("test_workflow"):
         # ... test code
@@ -539,10 +539,10 @@ poe test-e2e
 
 ```python
 # ❌ Flaky test
-flock = Flock("openai/gpt-4o-mini")  # Default temperature=1.0
+flock = Flock("openai/gpt-4.1")  # Default temperature=1.0
 
 # ✅ Deterministic test
-flock = Flock("openai/gpt-4o-mini", temperature=0)
+flock = Flock("openai/gpt-4.1", temperature=0)
 ```
 
 ### 2. Forgetting to Await `run_until_idle()`
@@ -614,7 +614,7 @@ async def test_unauthorized_access_blocked():
 
 ```python
 # ✅ Use small models for tests
-flock = Flock("openai/gpt-4o-mini")  # Faster than gpt-4.1
+flock = Flock("openai/gpt-4.1")
 
 # ✅ Use minimal data
 test_input = CodeSnippet(code="def foo(): pass")  # Not 1000 lines

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/docs/index.md

@@ -38,7 +38,7 @@ class Diagnosis(BaseModel):
     fix_suggestion: str
 
 # Create orchestrator
-flock = Flock("openai/gpt-4o-mini")
+flock = Flock("openai/gpt-4.1")
 
 # Declare agent with type contracts
 flock.agent("diagnostician") \

{flock_core-0.5.0b60 → flock_core-0.5.0b62}/docs/reference/index.md

@@ -63,7 +63,7 @@ Complete technical reference for Flock Flow API and configuration.
 #### Model Configuration
 ```bash
 # Default LLM model (LiteLLM format)
-DEFAULT_MODEL="openai/gpt-4o-mini"
+DEFAULT_MODEL="openai/gpt-4.1"
 
 # API keys for providers
 OPENAI_API_KEY="sk-..."
@@ -99,7 +99,7 @@ FLOCK_DASHBOARD_HOST="0.0.0.0"
 #### `.flock/config.yaml`
 ```yaml
 # Default model
-model: "openai/gpt-4o-mini"
+model: "openai/gpt-4.1"
 
 # Tracing settings
 tracing:
@@ -317,8 +317,8 @@ See [Changelog](https://github.com/whiteducksoftware/flock/releases) for complet
 
 ## Related Documentation
 
-- **[Getting Started](../getting-started/)** - Installation and quick start
-- **[User Guides](../guides/)** - Comprehensive guides
+- **[Getting Started](../getting-started/index.md)** - Installation and quick start
+- **[User Guides](../guides/index.md)** - Comprehensive guides
 - **[Examples](https://github.com/whiteducksoftware/flock/tree/main/examples)** - Working code examples
 
 ---