The branch permission check was only allowing feat/, feature/, and dev/
prefixes for write operations. This blocked PR creation from fix/*
branches, forcing fallback to direct API calls.
Added patterns:
- fix/, bugfix/, hotfix/ - for bug fixes
- chore/, refactor/ - for maintenance
- docs/, test/ - for documentation and tests
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace direct python path in .mcp.json with run.sh wrapper scripts
that automatically locate the venv in cache or local directory.
Problem: .venv symlinks are gitignored, causing them to be wiped on
every git operation. The SessionStart hook should recreate them but
this was unreliable, leading to repeated MCP server failures.
Solution: run.sh scripts that:
- First check ~/.cache/claude-mcp-venvs/leo-claude-mktplace/{server}/.venv
- Fallback to local .venv if exists
- Exit with helpful error if neither found
This eliminates dependency on symlinks entirely - the scripts are
tracked in git and will always be present after clone/pull/update.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add missing create_pull_request tool to Gitea MCP server. This completes
the PR lifecycle - previously only had list/get/review/comment tools.
- Add create_pull_request to GiteaClient
- Add async wrapper to PullRequestTools with branch permissions
- Register tool in server.py with proper schema
- Parameters: title, body, head, base, labels (optional)
- Branch-aware security: only allowed on development/feature branches
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The filter tool was adding an __index_level_0__ column to results
because pandas query() preserves the original index, which gets
converted to a column when storing the DataFrame.
Added .reset_index(drop=True) after query() to drop the preserved
index and create a clean sequential index.
Fixes#203
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add 34 tests across 3 test modules:
- test_parse_tools.py: 11 tests for README/CLAUDE.md parsing
- test_validation_tools.py: 11 tests for compatibility and agent validation
- test_report_tools.py: 12 tests for report generation and filtering
Coverage: parse_tools 79%, validation_tools 96%, report_tools 89%
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add report generation and issue listing tools:
- generate_compatibility_report: Full marketplace validation with
markdown or JSON output, includes summary statistics
- list_issues: Filtered issue listing by severity and type
The report tools coordinate parse_tools and validation_tools to
scan all plugins in a marketplace, run pairwise compatibility
checks, and aggregate findings into comprehensive reports.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add chart_create tool: create line, bar, scatter, pie, heatmap, histogram, area charts
- Add chart_configure_interaction tool: hover templates, click data, selection, zoom
- Support theme color integration when theme is active
- Default color palette based on Mantine theme
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add list_components tool: list DMC components by category
- Add get_component_props tool: get props schema with types/defaults/enums
- Add validate_component tool: validate props with error/warning messages
- Includes typo detection and common mistake warnings
- All tools registered in MCP server with proper JSON schemas
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add component_registry.py with version-locked registry loading
- Create dmc_2_5.json with 39 components for DMC 2.5.1/Mantine 7
- Add generate-dmc-registry.py script for future registry generation
- Update dependencies to DMC >=2.0.0 (installs 2.5.1)
- Includes prop validation with typo detection
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add viz-platform MCP server structure at mcp-servers/viz-platform/:
- mcp_server/server.py: Main MCP server entry point with async initialization
- mcp_server/config.py: Hybrid config loader with DMC version detection
- mcp_server/dmc_tools.py: Placeholder for DMC validation tools
- pyproject.toml and requirements.txt for dependencies
- tests/ directory structure
Server starts without errors with empty tool list.
Config detects DMC installation status via importlib.metadata.
Closes#170
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes#160: update_wiki_page was renaming pages to "unnamed"
Root causes:
1. page_name wasn't URL-encoded, breaking pages with special chars like ':'
2. PATCH request was missing 'title' field, causing Gitea to use default name
Changes:
- Add URL encoding (urllib.parse.quote) to get_wiki_page, update_wiki_page, delete_wiki_page
- Add 'title': page_name to update_wiki_page payload to preserve page name
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Expand parameter schemas for 15 update tools that previously only exposed
the 'id' field. The underlying Python implementation already supported
all fields via **kwargs, but Claude couldn't discover available parameters.
Updated tools:
- virtualization: update_virtual_machine, update_cluster
- dcim: update_site, update_location, update_rack, update_manufacturer,
update_device_type, update_device_role, update_platform,
update_interface, update_cable
- ipam: update_vrf, update_prefix, update_ip_address, update_vlan
Each tool now exposes all commonly-used optional fields matching the
NetBox API, following the pattern established by dcim_update_device.
Fixes#137
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Claude API has a 64-character limit on tool names. Claude Code uses a
36-character prefix (mcp__plugin_cmdb-assistant_netbox__), leaving only
28 characters for the actual tool name.
Shortened 33 tools that exceeded this limit:
- virtualization_* -> virt_* (19 tools)
- circuits_*_circuit_type* -> circ_*_type* (3 tools)
- circuits_*_circuit_termination* -> circ_*_termination* (3 tools)
- wireless_*_wireless_* -> wlan_* (8 tools)
Added TOOL_NAME_MAP to route shortened names to original method names.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes multiple issues from diagnostic #123:
1. create_label_smart type safety (labels.py)
- Add isinstance(result, dict) checks after API calls
- Return structured error dict if API returns unexpected type
- Prevents "list indices must be integers" crash
2. debug-report always uses curl with labels
- Remove MCP option - always use curl for marketplace issues
- Add label ID fetching step (Source/Diagnostic, Type/Bug)
- Include labels in curl POST payload
- Avoids branch protection restrictions on main branch
Fixes#123
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When NetBox MCP tools fail with JSON decode errors, the error message
now includes:
- HTTP status code
- Response content length
- Preview of actual content received (first 200 bytes)
This helps diagnose transient issues like network timeouts or
incomplete responses that result in cryptic "Expecting value" errors.
Fixes#120
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Expose additional parameters in dcim_create_device and dcim_update_device
MCP tools that were already supported by the backend but not exposed:
dcim_create_device:
- platform, primary_ip4, primary_ip6, asset_tag, description, comments
dcim_update_device:
- platform, primary_ip4, primary_ip6, serial, asset_tag, site, rack,
position, description, comments
This enables setting the platform (OS) and primary IP address when
creating or updating devices in NetBox.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
create_label_smart now checks if label already exists before creating.
- Checks both org and repo labels
- Handles format variations (Type/Bug vs Type: Bug)
- Returns {skipped: true} if label already exists
- Prevents duplicate label creation errors
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The suggest_labels tool accepted a repo parameter in the implementation
but didn't expose it in the MCP tool schema, causing it to always rely
on auto-detection which failed in some contexts.
Fixes#94
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The suggest_labels function now dynamically detects the label naming convention
used in the repository (slash format like Type/Bug or colon-space format like
Type: Bug) instead of hardcoding slash format.
Changes:
- Added _build_label_lookup() to parse and normalize label formats
- Added _find_label() to find actual labels from the lookup
- Updated suggest_labels() to accept optional repo parameter
- Labels are fetched first, then suggestions match actual names
- Supports Efforts/Effort normalization (handles singular/plural)
Fixes issue #73 sub-issue 3: label format mismatch
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The MCP server runs with cwd set to the plugin directory, not the
user's project directory. This caused git remote auto-detection to
fail because it was looking at the wrong directory.
Changes:
- Added _find_project_directory() method with multiple strategies:
1. CLAUDE_PROJECT_DIR environment variable
2. PWD environment variable (if it has .git or .env)
3. Current working directory (if it has .git or .env)
- Updated _detect_repo_from_git() to accept project_dir parameter
- Added 3 new tests for project directory detection
Fixes#70
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
1. Repo Auto-Detection (config.py):
- Added _detect_repo_from_git() to parse git remote URL
- Supports SSH, SSH short, HTTPS, HTTP URL formats
- Falls back to git remote when GITEA_REPO not set
2. Organization Validation (gitea_client.py):
- Changed is_org_repo() to use /orgs/{owner} endpoint
- Added _is_organization() method for reliable org detection
- Fixes issue where owner.type was null in Gitea API
3. Tests:
- Added 6 tests for git URL parsing
- Added 3 tests for org detection
Fixes#64
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The get_labels tool was failing with 404 for user-owned repositories
because it always queried /api/v1/orgs/{owner}/labels, which only
works for organizations.
Changes:
- labels.py: Check is_org_repo() before fetching org labels
- gitea_client.py: Same fix in _resolve_label_ids()
- test_labels.py: Added tests for both org and user-owned repos
Fixes#61
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update all references from old names to new marketplace identity:
- support-claude-mktplace → leo-claude-mktplace (URLs)
- lm-claude-plugins → leo-claude-mktplace (repo name)
- Claude Code Marketplace → Leo Claude Marketplace (display name)
Files updated:
- Core docs (CLAUDE.md, README.md, CHANGELOG.md)
- Documentation (CANONICAL-PATHS, CONFIGURATION, UPDATING, COMMANDS-CHEATSHEET)
- Marketplace manifest and all 9 plugin.json files
- Plugin READMEs and MCP server READMEs
- Setup script and label taxonomy reference
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Claude Code only caches the plugin directory when installed from a
marketplace, not parent directories. This broke the shared mcp-servers/
architecture because relative paths like ../../mcp-servers/ resolved
to non-existent locations in the cache.
Changes:
- Move gitea and wikijs MCP servers into plugins/projman/mcp-servers/
- Move netbox MCP server into plugins/cmdb-assistant/mcp-servers/
- Update .mcp.json files to use ${CLAUDE_PLUGIN_ROOT}/mcp-servers/
- Update setup.sh to handle new bundled structure
- Add netbox.env config template to setup.sh
- Update CLAUDE.md and CANONICAL-PATHS.md documentation
This ensures plugins work correctly when installed and cached.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove separate GITEA_OWNER config, use owner/repo format everywhere
- Add _parse_repo() helper to extract owner and repo from combined string
- Update plugin.json schema: file -> source, author as object
- Remove redundant configuration section from cmdb-assistant plugin
- Simplify gitea_client.py by removing excessive docstrings
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update git remote to new Tailscale hostname
- Replace old organization name (hhl-infra) with bandit
- Replace old repository name (claude-code-hhl-toolkit) with support-claude-mktplace
- Update all documentation references to use generic gitea.example.com
- Rebrand from HyperHive Labs to Bandit Labs across all files
- Rename workspace file to match new repository name
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem:
- Gitea API expects label IDs (integers), not label names (strings)
- Previous implementation passed label names directly, causing 422 errors
Solution:
- Added _resolve_label_ids() method to convert names to IDs
- Fetches all labels (org + repo) and builds name->ID mapping
- Automatically resolves IDs before creating issues
Testing:
- Created test issue #4 with 4 labels (manual verification)
- Created test issue #5 with 11 labels (automated testing)
- All labels applied correctly in Gitea
Also updated:
- projman/skills/label-taxonomy/labels-reference.md with current taxonomy
- Status updated to "Synced with Gitea" (43 labels total)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
