Skip to content

Conversation

@m1rl0k
Copy link
Collaborator

@m1rl0k m1rl0k commented Jan 27, 2026

No description provided.

Introduces a Redis pub/sub signal mechanism to trigger code indexing after bundle uploads, with a listener in watch_index.py that spawns ingest jobs. The VSCode extension now supports configuration for a dedicated auth backend URL and shared token, enabling non-interactive authentication flows for team deployments. Also bumps the extension version to 0.1.49.
Removed the ID column and hid advanced hash and graph columns in the admin collections table for a cleaner interface. Updated table and cell styling for improved readability. Added a new 'Team' section to the VSCode extension settings for shared authentication, and bumped the extension version to 0.1.50.
Added .cursorrules and GEMINI.md containing detailed rules and best practices for AI agents using Context-Engine MCP tools. Updated .gitignore to stop ignoring .cursorrules and GEMINI.md.
@kiloconnect
Copy link

kiloconnect bot commented Jan 27, 2026

Code Review Summary

Status: No Issues Found | Recommendation: Merge

Files Reviewed (9 files)
  • .cursorrules - New AI agent rules file
  • templates/admin/acl.html - UI changes to hide table columns
  • templates/admin/base.html - Table styling adjustments
  • uv.lock - Dependency updates
  • vscode-extension/build/publish-vscode-extension.sh - Executable permission change
  • vscode-extension/context-engine-uploader/auth_utils.js - Auth flow enhancements with new settings support
  • vscode-extension/context-engine-uploader/extension.js - Settings webview initialization update
  • vscode-extension/context-engine-uploader/package.json - Version bump and new configuration options
  • vscode-extension/context-engine-uploader/settings-webview.js - Added status monitoring section

@augmentcode
Copy link

augmentcode bot commented Jan 27, 2026

🤖 Augment PR Summary

Summary: This PR reduces redundant/incorrect indexing work and improves remote/team auth ergonomics.

Changes:

  • Adds a Redis pub/sub “index signal” emitted after a successful delta bundle upload, and a watcher-side listener to trigger ingest_code.
  • Updates spawn_ingest_code() to return a Popen handle so the watcher can hold a lock until ingest completes (avoiding concurrent ingests).
  • Tightens multi-repo detection to treat subdirectories as repos only when they contain a .git entry; improves related messaging.
  • Improves watcher repo-root detection by walking up to the nearest .git parent, with a legacy fallback.
  • Extends the VS Code uploader auth flow with backend URL normalization plus optional team settings (authBackendUrl, authSharedToken).
  • Simplifies/admin UI tables by hiding some columns and tweaking table layout/spacing.
  • Adds/updates AI-agent rule documents (.cursorrules, GEMINI.md, skills/docs) and adjusts .gitignore accordingly.
  • Aligns the pinned mcp dependency version across pyproject.toml and requirements.txt.

Technical Notes: The watcher’s Redis listener spawns ingest in a background subprocess and uses a lock to skip overlapping signals; auth URL normalization now preserves path-prefixed backends (e.g. /upload).

🤖 Was this summary useful? React with 👍 or 👎

Copy link

@augmentcode augmentcode bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Review completed. 3 suggestions posted.

Fix All in Augment

Comment augment review to trigger a new review at any time.

Expanded documentation in .cursorrules, GEMINI.md, and SKILL.md to emphasize that 'symbol_graph' is the default and always-available tool for code graph queries, and clarified when to use or avoid 'neo4j_graph_query', grep, and file reading. Updated mcp version in pyproject.toml and requirements.txt for consistency. Added uv.lock for dependency management.
Updated SKILL.md and CLAUDE.example.md to explicitly discourage using grep, Read File, and similar filesystem tools for code exploration. Added clear guidance to always prefer MCP tools (repo_search, symbol_graph, etc.) for exploration, debugging, and structural queries, reserving literal search/file reads only for exact string matches or files already located via MCP. Clarified tool availability and fallback behavior for symbol_graph and neo4j_graph_query.
Python scripts now detect git repositories by presence of .git directories, preventing subdirectories from being misclassified as repos. The VSCode extension refactors backend URL normalization into a shared function, reducing duplication and improving consistency in auth-related flows.
@m1rl0k
Copy link
Collaborator Author

m1rl0k commented Jan 27, 2026

augment review

Copy link

@augmentcode augmentcode bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Review completed. 3 suggestions posted.

Fix All in Augment

Comment augment review to trigger a new review at any time.

const configuredAuthBackendUrl = (settings.get('authBackendUrl') || '').trim();
const configuredAuthToken = (settings.get('authSharedToken') || '').trim();

let backendUrl = normalizeBackendUrl(explicitBackendUrl || configuredAuthBackendUrl || endpoint);
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

runAuthLoginFlow() prefers explicitBackendUrl over the new contextEngineUploader.authBackendUrl, so if callers pass the regular endpoint as the explicit URL this setting may never take effect. Can you confirm the intended precedence here?

Fix This in Augment

🤖 Was this useful? React with 👍 or 👎

Enhanced multi-repo mode to prefer directories with .git, but fall back to treating all subdirectories as repos if none are found, improving resilience in K8s/container environments. Updated documentation and logging to clarify behavior. Also canonicalized working directory in CLI for macOS compatibility and fixed file permissions for the VSCode extension publish script.
Introduces a new 'Status' section in the settings webview to display live indexing progress and system status. Adds UI components, styles, and polling logic to fetch and display real-time status from the backend. The default section is now 'Status', and the webview's CSP is updated to allow connections to the configured endpoint.
In qdrant.py, remote embedding now chunks large batches to respect the service's max batch size, improving reliability for large inputs. watch_index.py adds a check to skip signals with empty workspace_path, preventing unnecessary processing. In auth_utils.js, backend URL selection for login and logout now consistently prefers the configured authBackendUrl, ensuring settings override and alignment between login and logout flows.
Split the reset logic into modular helper functions for full and partial resets, improving readability and maintainability. The new structure separates concerns for stopping services, building containers, clearing caches, and starting the indexer, and provides clearer progress output. Also, minor cleanup in docker-compose.yml.
@m1rl0k m1rl0k merged commit c7c0c3b into test Jan 27, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants