chore(release): bump version to 0.5.2 - #67
Conversation
📝 WalkthroughWalkthroughThis PR updates the repository versioning to 0.5.2 across workspace Cargo manifests and published package manifests, adds example workflows (email-ingestor, model-router), example runners and handlers, and performs small test and formatting edits in the YAML runner code. ChangesVersion 0.5.2 Release
Examples, Workflows, Handlers, and Tests
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Aligns the standalone wasm crate lockfile with the package version bump. Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Introduce HR/Finance/Education email classification with per-subtype routing, financial audit custom workers, and a streaming runner with optional OTLP tracing. Co-authored-by: Cursor <cursoragent@cursor.com>
Route developer queries by task domain with d-flash repeat detection and a streaming runner for local OpenAI-compatible model endpoints. Co-authored-by: Cursor <cursoragent@cursor.com>
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@examples/python-test-simpleAgents/runners/run_model_router.py`:
- Around line 28-43: The docstring for the on_event callback is inaccurate: it
describes token/snapshot-specific stdout/stderr behavior but the implementation
simply prints the raw event object (print(event)). Update the docstring of the
callback function (referenced as default_on_event / on_event in this module) to
accurately state that the function prints the raw event to stdout and does not
perform token or snapshot-specific formatting or stderr logging, or
alternatively implement the described token/snapshot formatting to match the
docstring — pick one and make the docstring and the function body consistent.
In `@examples/python-test-simpleAgents/workflows/model-router/model-router.yaml`:
- Line 21: Update the workflow metadata description to accurately reflect the
configured model(s): replace the current text mentioning “Gemma/Qwen models” in
the description field with a concise description that references the actual
model id used (mlx-community/LFM2-8B-A1B-4bit) and the d-flash repeat detection
behavior; locate the description key in model-router.yaml and edit its value to
match the real routing targets and functionality.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: db30a5c3-d11c-4183-aa44-73574aa539a7
⛔ Files ignored due to path filters (1)
bindings/wasm/simple-agents-wasm/rust/Cargo.lockis excluded by!**/*.lock
📒 Files selected for processing (8)
crates/simple-agents-workflow/src/yaml_runner/client_executor.rscrates/simple-agents-workflow/src/yaml_runner/tests.rsexamples/python-test-simpleAgents/example_env.pyexamples/python-test-simpleAgents/runners/run_email_ingestor.pyexamples/python-test-simpleAgents/runners/run_model_router.pyexamples/python-test-simpleAgents/workflows/email-ingestor/email-ingestor.yamlexamples/python-test-simpleAgents/workflows/email-ingestor/handlers.pyexamples/python-test-simpleAgents/workflows/model-router/model-router.yaml
✅ Files skipped from review due to trivial changes (2)
- crates/simple-agents-workflow/src/yaml_runner/client_executor.rs
- crates/simple-agents-workflow/src/yaml_runner/tests.rs
| """Print streamed tokens to stdout; log structured snapshots to stderr. | ||
|
|
||
| A ready-made ``on_event`` callback suitable for quick scripts and demos. | ||
| Pass it directly wherever a callback is accepted:: | ||
|
|
||
| from simple_agents_py.workflow_stream import default_on_event | ||
| client.stream_workflow(payload, on_event=default_on_event) | ||
|
|
||
| Prints ``node_stream_delta``, ``node_stream_thinking_delta``, and | ||
| ``node_stream_output_delta`` tokens inline on **stdout** (no newline between | ||
| tokens). Emits a single line per ``node_stream_snapshot`` event on **stderr** | ||
| (healing / structured JSON snapshot progress: node id, optional metadata, JSON | ||
| preview). Silently ignores ``workflow_started`` and ``workflow_completed``; | ||
| all other event types are also silently ignored by this handler. | ||
| """ | ||
| print(event) |
There was a problem hiding this comment.
Align callback docstring with actual behavior.
Line 28–42 describes token/snapshot-specific stdout/stderr handling, but Line 43 only prints the raw event object. This is misleading for users copying this example.
✏️ Proposed fix (docstring aligned to implementation)
def default_on_event(event: WorkflowStreamEvent) -> None:
- """Print streamed tokens to stdout; log structured snapshots to stderr.
-
- A ready-made ``on_event`` callback suitable for quick scripts and demos.
- Pass it directly wherever a callback is accepted::
-
- from simple_agents_py.workflow_stream import default_on_event
- client.stream_workflow(payload, on_event=default_on_event)
-
- Prints ``node_stream_delta``, ``node_stream_thinking_delta``, and
- ``node_stream_output_delta`` tokens inline on **stdout** (no newline between
- tokens). Emits a single line per ``node_stream_snapshot`` event on **stderr**
- (healing / structured JSON snapshot progress: node id, optional metadata, JSON
- preview). Silently ignores ``workflow_started`` and ``workflow_completed``;
- all other event types are also silently ignored by this handler.
- """
+ """Print each streamed workflow event (debug/demo callback)."""
print(event)🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@examples/python-test-simpleAgents/runners/run_model_router.py` around lines
28 - 43, The docstring for the on_event callback is inaccurate: it describes
token/snapshot-specific stdout/stderr behavior but the implementation simply
prints the raw event object (print(event)). Update the docstring of the callback
function (referenced as default_on_event / on_event in this module) to
accurately state that the function prints the raw event to stdout and does not
perform token or snapshot-specific formatting or stderr logging, or
alternatively implement the described token/snapshot formatting to match the
docstring — pick one and make the docstring and the function body consistent.
|
|
||
| metadata: | ||
| name: "Dev Task Model Router" | ||
| description: "Route developer queries to Gemma/Qwen models with d-flash repeat detection" |
There was a problem hiding this comment.
Update metadata description to match configured models.
Line 21 says “Gemma/Qwen models,” but this workflow routes to mlx-community/LFM2-8B-A1B-4bit in all execution paths. Please sync the description with the actual configuration.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@examples/python-test-simpleAgents/workflows/model-router/model-router.yaml`
at line 21, Update the workflow metadata description to accurately reflect the
configured model(s): replace the current text mentioning “Gemma/Qwen models” in
the description field with a concise description that references the actual
model id used (mlx-community/LFM2-8B-A1B-4bit) and the d-flash repeat detection
behavior; locate the description key in model-router.yaml and edit its value to
match the real routing targets and functionality.
Summary by CodeRabbit