* Update retired model ids in settings components and docs
* Fix CLI default and sync generated dashboard copies
Two gaps from the first commit:
1. evaluation.py only had the function signature default updated. The
argparse `--model` default still pointed at the retired model, and
since `args.model` is always passed explicitly to run_evaluation, that
CLI value overrode the new default. Anyone running the script without
-m still got the retired model, so the change had no practical effect.
The usage example and reference/evaluation.md carried the same stale
ID.
2. The settings components under cli-tool/ were updated but their
generated copies under dashboard/public/component-content/ were not,
so the public dashboard would keep serving the retired IDs. Copies are
now regenerated from their sources rather than hand-edited.
---------
Co-authored-by: kasparovabi <kasparovabi@users.noreply.github.com>
Adds a 'doordash' category of components built on doordash-oss/doordash-cli
(dd-cli), focused on what plain prompting cannot deliver: persistent state,
deterministic enforcement, and multi-person coordination.
- dd-order-playbooks: named saved orders with mandatory cart-diff on recall
- dd-spend-guard: budget caps enforced by dd-guard.sh wrapper + PreToolUse
hook denying bypasses (per-order/daily/weekly/monthly, cooldown, hours)
- dd-allergy-shield: persistent dietary profile, vetted-cart dumps re-grepped
by a deterministic checkout gate for anaphylaxis-tier allergens
- dd-group-orders: team roster, person-to-cart-item-id ledger, cost split,
payer rotation, live allergen re-check at group checkout
- dd-order-ledger: PostToolUse audit log (secrets stripped) + /dd-report
All hook/wrapper scripts behaviorally tested with stubs (block/allow paths,
staleness state machine, attribution, secret stripping). Real-binary testing
pending on Apple Silicon (dd-cli is darwin-arm64 only).
Also: cloudflare-pages-deployment-monitor statusline (self-contained bash,
env-based config) and a testing-gate step in the component workflow docs.
Codebase explorer agent, deadline countdown statusline, change logger
hook, deadline prep skill, commit smart skill, and test detect skill.
Designed for rapid onboarding on unfamiliar codebases with time pressure.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New global setting to display custom announcements in Claude Code.
Users can replace the example messages with their own org announcements.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New global setting to customize Claude Code spinner tips with custom messages.
Users can replace the default tips array and toggle excludeDefault.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Previously used endpoints[0] which could return the wrong branch's
compute (e.g., development/idle instead of production/active).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add 4 new Z.AI MCP integrations (vision, web-reader, web-search, zread)
- Update GLM model from 4.6 to 4.7 in coding plan
- Migrate website URLs from GitHub Pages to aitmpl.com
- Update component catalog with latest download stats
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Fixes file reading error on Windows where the default encoding (cp949)
fails to read UTF-8 transcript files. Adding explicit encoding='utf-8'
with errors='replace' ensures cross-platform compatibility.
- Update local settings and configurations
- Add Vertex AI Claude Code integration blog post
- Sync analytics components and documentation
- Remove test data files and update configurations
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated descriptions for RPG status bar and virtual code garden to include display details.
- Modified component documentation to reflect new features and descriptions for various statuslines.
- Removed max-height restrictions in CSS for better component visibility.
- Adjusted modal helper to show full component descriptions instead of truncated versions.
- Introduced settings for Amazon Bedrock, Google Vertex AI, and corporate proxy configurations.
- Added custom headers support for API requests.
- Implemented API key helper for dynamic authentication token generation.
- Restricted login methods to Claude.ai and Anthropic Console accounts.
- Configured bash command execution timeouts and performance optimizations.
- Enhanced privacy settings by disabling telemetry and non-essential traffic.
- Established AWS credential management for Bedrock integration.
- Allowed additional directory access and common git operations.
- Created comprehensive permissions for development and read-only modes.
- Developed various status line configurations for improved user experience.
- Add 9 Settings components (telemetry, permissions, model, cleanup)
- Add 6 Hooks components (formatting, git integration, backups, testing)
- Implement CLI installation with --setting and --hook flags
- Add conflict detection that prompts user before overwriting
- Merge settings into .claude/settings.json with intelligent deep merge
- Update data-loader.js to handle new component types
- Add filter buttons for Settings and Hooks in web interface
- Generate components.json with new Settings and Hooks sections
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Dani