minor fix

.github/workflows/examples-chartqa.yml

@@ -2,8 +2,25 @@ name: Examples - ChartQA
 permissions:
   contents: read
 on:
+  schedule:
+    # Every day at 6 AM UTC+8
+    - cron: "0 22 * * *"
+
   workflow_dispatch:
 
+  repository_dispatch:
+    types: [ci-chartqa, ci-all]
+
+run-name: >-
+  ${{ github.event_name == 'repository_dispatch'
+      && format(
+        'ChartQA - PR #{0} - {1} - {2}',
+        github.event.client_payload.pull_number,
+        github.event.client_payload.ci_label,
+        github.event.client_payload.correlation_id
+      )
+      || format('ChartQA - {0}', github.event_name) }}
+
 jobs:
   chartqa:
     if: >

.github/workflows/tests.yml

@@ -19,7 +19,7 @@ jobs:
   lint:
     strategy:
       matrix:
-        setup: [fast, slow]
+        setup: [fast, slow, next]
       fail-fast: false
     name: Lint - ${{ matrix.setup }}
     runs-on: ubuntu-latest
@@ -33,6 +33,9 @@ jobs:
       - name: Sync dependencies (fast)
         run: uv sync --frozen --group dev --no-default-groups
         if: matrix.setup == 'fast'
+      - name: Upgrade dependencies (next)
+        run: uv lock --upgrade
+        if: matrix.setup == 'next'
       - name: Sync dependencies (slow)
         run: |
           uv sync --frozen \
@@ -47,7 +50,7 @@ jobs:
             --group agents \
             --group langchain \
             --no-default-groups
-        if: matrix.setup == 'slow'
+        if: matrix.setup != 'fast'
       # This pre-commit skips JavaScript on purpose.
       - name: Run pre-commit
         uses: pre-commit/action@v3.0.1
@@ -62,7 +65,7 @@ jobs:
         if: matrix.setup == 'fast'
       - name: Run pyright (slow)
         run: uv run --locked --no-sync pyright -p pyrightconfig.json
-        if: matrix.setup == 'slow'
+        if: matrix.setup != 'fast'
 
   lint-js:
     name: Lint - JavaScript

agentlightning/verl/entrypoint.py

@@ -34,6 +34,9 @@ __all__ = [
 
 @hydra.main(config_path="pkg://agentlightning/verl", config_name="config", version_base=None)
 def main(config: Any):
+    from .daemon import AgentModeDaemon
+    from .trainer import AgentLightningTrainer
+
     run_ppo(
         config,
         train_dataset=None,

contrib/CODEOWNERS

@@ -1 +1,4 @@
 # Put code owner definitions here.
+
+# Recipes
+recipes/search_r1 @SiyunZhao @JiahangXu

contrib/recipes/search_r1/README.md

@@ -2,7 +2,7 @@
 
 ## Overview
 
-This example implements **Search R1** within Agent Lightning. It also serves as a demonstration of a **framework-free agent training pipeline**, showing how to run end-to-end RL training without relying on specialized frameworks. **It's tested and compatible with Agent-lightning v0.1.x**.
+This example implements **Search R1** within Agent Lightning. It also serves as a demonstration of a **framework-free agent training pipeline**, showing how to run end-to-end RL training without relying on specialized frameworks. **It's tested and compatible with Agent-lightning v0.1.2**.
 
 The example is designed to run on a single node with 8 GPUs, each having at least 40 GB of memory.
 

examples/README.md

@@ -2,6 +2,8 @@
 
 This catalog highlights the examples shipped with Agent-lightning.
 
+Community-contributed examples and recipes are available in the [contrib](../contrib) directory.
+
 | Example | Description | CI Maintenance |
 |---------|-------------|----------------|
 | [apo](./apo) | Automatic Prompt Optimization tutorials covering built-in, custom, and debugging workflows. | [![apo workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-apo.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-apo.yml) |
@@ -11,9 +13,23 @@ This catalog highlights the examples shipped with Agent-lightning.
 | [claude_code](./claude_code) | Claude Code SWE-bench harness that records Agent-lightning traces across Anthropic, vLLM, and OpenAI-compatible backends. | [![claude_code workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-claude-code.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-claude-code.yml) |
 | [minimal](./minimal) | Bite-sized programs that demonstrate how individual Agent-lightning building blocks behave in isolation. | [![minimal workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-unit.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/badge-unit.yml) |
 | [rag](./rag) | Retrieval-Augmented Generation pipeline targeting the MuSiQue dataset with Wikipedia retrieval. | [![rag workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-rag.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-rag.yml) |
-| [search_r1](./search_r1) | Framework-free Search-R1 reinforcement learning training workflow with a retrieval backend. | **Last verified with Agent-lightning v0.1.2** |
 | [spider](./spider) | Text-to-SQL reinforcement learning training on the Spider dataset using LangGraph. | [![spider workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-spider.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-spider.yml) |
 | [tinker](./tinker) | Reinforcement learning with Tinker as the backend training service. | [![tinker workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-tinker.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-tinker.yml) |
 | [unsloth](./unsloth) | Supervised fine-tuning example powered by Unsloth with 4-bit quantization and LoRA. | [![unsloth workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-unsloth.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-unsloth.yml) |
 
-*NOTE: CI status avoids taking any workflow running with latest dependencies into account. That's why we reference the corresponding `badge-*` workflows instead. Each example's own README also displays its `examples-*` workflow status whenever the project is maintained by CI.*
+## `examples-*` workflow status
+
+CI status above avoids taking any workflow running with latest dependencies into account. That's why we reference the corresponding `badge-*` workflows instead. The following table displays the raw `examples-*` workflow status whenever the project is maintained by CI.
+
+| Workflow | Status |
+|----------|--------|
+| `examples-apo.yml` | [![examples-apo workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-apo.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-apo.yml) |
+| `examples-azure.yml` | [![examples-azure workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-azure.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-azure.yml) |
+| `examples-calc-x.yml` | [![examples-calc-x workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-calc-x.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-calc-x.yml) |
+| `examples-chartqa.yml` | [![examples-chartqa workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-chartqa.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-chartqa.yml) |
+| `examples-claude-code.yml` | [![examples-claude-code workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-claude-code.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-claude-code.yml) |
+| `examples-compat.yml` | [![examples-compat workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-compat.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-compat.yml) |
+| `examples-rag.yml` | [![examples-rag workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-rag.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-rag.yml) |
+| `examples-spider.yml` | [![examples-spider workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-spider.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-spider.yml) |
+| `examples-tinker.yml` | [![examples-tinker workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-tinker.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-tinker.yml) |
+| `examples-unsloth.yml` | [![examples-unsloth workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-unsloth.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-unsloth.yml) |