Feat/kaizen policies - #68
Merged
Merged
Conversation
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📒 Files selected for processing (2)
📝 WalkthroughWalkthroughAdds a generic MCP tool Changes
Sequence Diagram(s)sequenceDiagram
participant Client as Client
participant MCP as MCP_Server
participant Search as EntityStore/Search
participant FS as Filesystem
Client->>MCP: get_entities(task, entity_type)
MCP->>Search: search_entities(filters: {type: entity_type}, task)
Search-->>MCP: list of Entity objects
MCP->>FS: read/ensure_namespace metadata
FS-->>MCP: namespace metadata (num_entities, etc.)
MCP-->>Client: formatted response ("# {EntityType}s for: {task}" + items)
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~22 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@kaizen/backend/filesystem.py`:
- Around line 222-223: The delete path leaves persisted
FilesystemNamespace.num_entities stale because we only update num_entities when
adding; in delete_entity_by_id update the in-memory namespace data's
num_entities (set data.num_entities = len(data.entities) or equivalent) before
calling self._save_namespace_data so saved metadata stays in sync with the
actual entities; modify delete_entity_by_id to update num_entities and then call
_save_namespace_data.
In `@tests/unit/test_policy_schema.py`:
- Around line 1-8: Add the pytest "unit" marker to the test module so it runs
under -m unit: either set a module-level marker by adding pytestmark =
pytest.mark.unit at the top of tests/unit/test_policy_schema.py (above imports
or right after them) or decorate each test function with `@pytest.mark.unit`;
ensure you import pytest if not already present.
ℹ️ Review info
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
AGENTS.mdREADME.mddocs/POLICIES.mdkaizen/backend/filesystem.pykaizen/frontend/mcp/mcp_server.pykaizen/schema/policy.pytests/unit/test_policy_schema.py
- Added Policy schema mirroring CUGA models - Enhanced MCP server with generic get_entities tool - Restored get_guidelines as a backward-compatible alias - Fixed num_entities bug in Filesystem backend - Added dedicated policy documentation and unit tests
visahak
force-pushed
the
feat/kaizen-policies
branch
from
February 23, 2026 20:46
3039262 to
ec4c0a9
Compare
This commit fixes the stale num_entities when deleting a filesystem entity, removes the missing ensure_namespace function call from the mcp_server after the upstream rebase, and adds a module-level pytest unit mark to the policy schema tests.
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (2)
kaizen/frontend/mcp/mcp_server.py (1)
78-78:capitalize()produces malformed headers for underscore-separated entity types.
"intent_guard".capitalize()→"Intent_guard", giving headers like# Intent_guards for: …. Consider replacing underscores before capitalising.✨ Suggested improvement
- header = f"# {entity_type.capitalize()}s for: {task}" + header = f"# {entity_type.replace('_', ' ').title()}s for: {task}"🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@kaizen/frontend/mcp/mcp_server.py` at line 78, The header generation uses entity_type.capitalize() which leaves underscores intact (e.g., "Intent_guard"); update the header creation (the header variable assignment) to replace underscores and properly title-case the entity type before pluralizing—e.g., transform entity_type with entity_type.replace("_", " ").title() (or split and capitalize each word) and then use that result in f"# {…}s for: {task}" so headers read "Intent Guards for: …".kaizen/schema/policy.py (1)
26-26:thresholdhas no range constraint — invalid values (e.g.2.5,-0.1) are silently accepted.🛡️ Suggested validation
- threshold: float = 0.7 # for natural_language triggers + threshold: float = Field(default=0.7, ge=0.0, le=1.0) # for natural_language triggers🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@kaizen/schema/policy.py` at line 26, The threshold field currently accepts any float; add validation to enforce 0.0 <= threshold <= 1.0 by adding a check where the containing class is initialized (e.g., implement a __post_init__ for dataclasses or a validate_threshold/validator for pydantic models) that raises ValueError if threshold is out of range, or replace the declaration with a pydantic Field(threshold: float = Field(0.7, ge=0.0, le=1.0)) to enforce the bounds automatically; reference the threshold symbol and the class that declares it when adding this validation.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@docs/POLICIES.md`:
- Around line 17-19: The TriggerType.ALWAYS option is missing from the trigger
list in the docs; update the "Trigger Types" section to include `always` (e.g.,
describe that `always` triggers apply to every input/response such as global
output formatters) so the docs match the policy.py schema and references to
TriggerType.ALWAYS.
In `@kaizen/frontend/mcp/mcp_server.py`:
- Around line 66-84: The call to the undefined function ensure_namespace()
inside get_entities_logic causes a NameError and is redundant because
get_client() already initializes the namespace; remove the ensure_namespace()
call from get_entities_logic (and any other occurrences in this module such as
in get_entities or get_guidelines if present) so the function relies on
get_client()'s internal _namespace_initialized logic and no longer references
the undefined symbol.
In `@kaizen/schema/policy.py`:
- Around line 1-3: Replace deprecated typing generics in the imports and model
annotations: remove List, Dict, Optional from the typing import and use built-in
generics (list, dict) and PEP 604 union syntax (T | None) for optional fields
used in your Pydantic models; update any field annotations that referenced
List[...] to list[...], Dict[...] to dict[..., ...], and Optional[T] to T |
None, keeping Enum, BaseModel, Field, and Any as needed (e.g., adjust model
classes that reference these types in kaizen/schema/policy.py such as any
BaseModel subclasses and their field definitions).
---
Nitpick comments:
In `@kaizen/frontend/mcp/mcp_server.py`:
- Line 78: The header generation uses entity_type.capitalize() which leaves
underscores intact (e.g., "Intent_guard"); update the header creation (the
header variable assignment) to replace underscores and properly title-case the
entity type before pluralizing—e.g., transform entity_type with
entity_type.replace("_", " ").title() (or split and capitalize each word) and
then use that result in f"# {…}s for: {task}" so headers read "Intent Guards
for: …".
In `@kaizen/schema/policy.py`:
- Line 26: The threshold field currently accepts any float; add validation to
enforce 0.0 <= threshold <= 1.0 by adding a check where the containing class is
initialized (e.g., implement a __post_init__ for dataclasses or a
validate_threshold/validator for pydantic models) that raises ValueError if
threshold is out of range, or replace the declaration with a pydantic
Field(threshold: float = Field(0.7, ge=0.0, le=1.0)) to enforce the bounds
automatically; reference the threshold symbol and the class that declares it
when adding this validation.
ℹ️ Review info
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
AGENTS.mdREADME.mddocs/POLICIES.mdkaizen/backend/filesystem.pykaizen/frontend/mcp/mcp_server.pykaizen/schema/policy.pytests/unit/test_policy_schema.py
🚧 Files skipped from review as they are similar to previous changes (2)
- kaizen/backend/filesystem.py
- tests/unit/test_policy_schema.py
Modernized typing generics in policy schema using built-in list/dict and PEP 604 union syntax. Updated documentation to include the missing "always" trigger type.
Collaborator
Author
|
ready to be reviewed |
Collaborator
|
@visahak just wanna make sure i understand it correctly, this change is to support create policy manually and store it in kaizen but extract policies from trajectories is not supported yet? |
Collaborator
Author
Yes |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary by CodeRabbit
New Features
Documentation
Bug Fixes
Tests