Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: logs and pipeline query api #636

Merged
merged 1 commit into from
Dec 26, 2024
Merged

fix: logs and pipeline query api #636

merged 1 commit into from
Dec 26, 2024

Conversation

JarbasAl
Copy link
Member

@JarbasAl JarbasAl commented Dec 19, 2024

skip common_qa when checking intent via bus api

Summary by CodeRabbit

  • New Features

    • Integrated PadaciosoService for improved intent handling.
    • Enhanced logging for skill interactions during conversations.
  • Bug Fixes

    • Adjusted intent matching logic to skip specific pipelines, refining intent retrieval process.
  • Documentation

    • Updated logging statements to improve traceability of utterance parsing and skill engagement.

skip common_qa when checking intent via bus api
Copy link

coderabbitai bot commented Dec 19, 2024

Walkthrough

The pull request introduces modifications to the intent services in the OVOS core. The changes primarily focus on the IntentService class in the ovos_core/intent_services/__init__.py file, where the PadaciosoService import is activated and the intent handling logic is updated. Additionally, a debug logging statement is added to the ConverseService class in ovos_core/intent_services/converse_service.py to improve traceability of skill interactions during conversation processing.

Changes

File Change Summary
ovos_core/intent_services/__init__.py - Activated PadaciosoService import
- Updated _load_pipeline_plugins to ensure PadaciosoService instantiation
- Modified handle_get_intent to skip specific pipelines during intent matching
- Enhanced logging in handle_utterance method
ovos_core/intent_services/converse_service.py - Added debug logging in converse_with_skills method to log skill conversation attempts

Sequence Diagram

sequenceDiagram
    participant IntentService
    participant PadaciosoService
    participant Skills

    IntentService->>PadaciosoService: Load Pipeline
    IntentService->>Skills: Handle Utterance
    Skills-->>IntentService: Potential Responses
    IntentService->>IntentService: Filter Pipelines
    IntentService-->>Skills: Final Intent Matching
Loading

Possibly related PRs

Suggested labels

fix

Suggested reviewers

  • goldyfruit

Poem

🐰 In the realm of intents so bright,
Pipelines dance with newfound might
Logging skills with rabbit's glee
OVOS core, now more free!
A hop, a skip, intent's delight! 🌟


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between a4a15a2 and 5872f60.

📒 Files selected for processing (2)
  • ovos_core/intent_services/__init__.py (3 hunks)
  • ovos_core/intent_services/converse_service.py (1 hunks)
🔇 Additional comments (3)
ovos_core/intent_services/converse_service.py (1)

338-338: LGTM! Improved logging for skill conversation attempts.

The added debug log enhances system observability by tracking which skills are being attempted for conversation.

ovos_core/intent_services/__init__.py (2)

35-35: LGTM! Clean import of PadaciosoService.

The import statement is properly aliased and aligns with its usage in the _load_pipeline_plugins method.


358-358: LGTM! Enhanced logging and pipeline filtering.

The changes improve the system by:

  1. Adding debug logging for utterance parsing
  2. Implementing the requested pipeline skipping in handle_get_intent

The modifications align with the PR objective to skip common_qa during intent checking via the bus API.

Let's verify the impact of skipping these pipelines:

Also applies to: 469-472

✅ Verification successful

Skipping optional pipelines in handle_get_intent is safe

The verification confirms that skipping common_qa, converse, and fallback pipelines in handle_get_intent is safe because:

  1. These pipelines are optional and not part of the core intent matching flow
  2. The skipped pipelines are typically used as fallback mechanisms when no direct intent match is found
  3. The main intent matching pipelines (adapt, padatious, padacioso) remain active
  4. The implementation shows these are separate services that can be safely excluded for direct intent queries
🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Verify that skipped pipelines are not critical for intent matching
# Test: Search for direct usage of skipped pipelines in intent matching

# Check for direct references to common_qa in intent matching
rg -l "common_qa.*intent" --type py

# Check for direct references to fallback pipelines in intent matching
rg -l "fallback_(high|medium|low).*intent" --type py

# Check for direct references to converse in intent matching
rg -l "converse.*intent" --type py

Length of output: 305


Script:

#!/bin/bash
# Let's check the actual usage context of these pipelines

# Check fallback pipeline usage in stop service
rg "fallback_(high|medium|low).*intent" -A 5 -B 5 ovos_core/intent_services/stop_service.py

# Check converse intent usage in test files
rg "converse.*intent" -A 5 -B 5 test/end2end/session/test_get_response.py test/end2end/session/test_converse.py

# Let's also check the handle_get_intent implementation to understand the pipeline skipping
ast-grep --pattern 'def handle_get_intent($$$)'

Length of output: 7754


Script:

#!/bin/bash
# Let's check the actual implementation of handle_get_intent to understand pipeline skipping
rg "def handle_get_intent" -A 20 ovos_core/intent_services/__init__.py

# Also check if these pipelines are used in any critical intent matching paths
rg "common_qa|fallback_(high|medium|low)|converse" -A 5 -B 5 ovos_core/intent_services/__init__.py

Length of output: 8270


Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@github-actions github-actions bot added the fix label Dec 19, 2024
Copy link

codecov bot commented Dec 19, 2024

Codecov Report

Attention: Patch coverage is 33.33333% with 2 lines in your changes missing coverage. Please review.

Project coverage is 72.30%. Comparing base (23f0bab) to head (5872f60).
Report is 158 commits behind head on dev.

Files with missing lines Patch % Lines
ovos_core/intent_services/__init__.py 50.00% 1 Missing ⚠️
ovos_core/intent_services/converse_service.py 0.00% 1 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##              dev     #636      +/-   ##
==========================================
- Coverage   75.33%   72.30%   -3.04%     
==========================================
  Files          15       15              
  Lines        3094     1585    -1509     
==========================================
- Hits         2331     1146    -1185     
+ Misses        763      439     -324     
Flag Coverage Δ
unittests 49.40% <33.33%> (-25.94%) ⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@github-actions github-actions bot added fix and removed fix labels Dec 19, 2024
@JarbasAl JarbasAl merged commit 05fbda5 into dev Dec 26, 2024
5 of 8 checks passed
@JarbasAl JarbasAl deleted the logs branch December 26, 2024 22:00
@coderabbitai coderabbitai bot mentioned this pull request Jan 31, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant