feat: standardize tour-operator-config-agent for multi-provider support#1140
feat: standardize tour-operator-config-agent for multi-provider support#1140ashleyshaw wants to merge 17 commits into
Conversation
|
✅ Template check passed after update. Thanks for fixing the PR description. |
|
Warning Review limit reached
Next review available in: 27 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Repository YAML (base), Organization UI (inherited) Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (29)
✨ 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 |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 8fd4f7e0ae
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| providers: | ||
| - claude | ||
| - copilot | ||
| - openai |
There was a problem hiding this comment.
When this agent is validated or selected through OpenAI, it cannot load because the commit declares openai active but neither openai/agent.md nor openai/tools.json exists anywhere in the repository. The checks.yml workflow runs validate:agent-hooks, whose multi-provider consistency checker rejects every declared provider without its corresponding agent.md, so this also blocks the checks job once dependencies are installed.
Useful? React with 👍 / 👎.
| @@ -0,0 +1,75 @@ | |||
| [ | |||
There was a problem hiding this comment.
When the standardised provider configuration is validated or ingested, this top-level array is rejected by schema/provider-config.schema.json, which requires an object containing a provider field and expects tool definitions under tools (as used by the Playwright agent). Wrap this list in the Claude provider envelope so the newly advertised Claude tool integration can be loaded through the repository's provider-config contract.
Useful? React with 👍 / 👎.
| ## Related Resources | ||
|
|
||
| - Claude Config: `claude/agent.md` + `claude/tools.json` | ||
| - Copilot Config: `copilot/agent.md` + `copilot/skills.yaml` |
There was a problem hiding this comment.
When deploying this configuration to Copilot, the advertised commands have no skill bindings because copilot/skills.yaml is referenced here but is absent after a repository-wide file search. The other standardised agents provide this file, and the initiative's Copilot packaging contract uses it to map skill names to sources; include it or stop advertising the Copilot configuration as complete.
Useful? React with 👍 / 👎.
ashleyshaw
added
type:feature
⏱️ Aging and SLA annotation
Maintained by project-meta-sync workflow. |
Metadata governance
|
github-actions
Bot
added
status:needs-review
🔍 Reviewer Summary for PR #1140CI Status: ✅ Recommendations
|
github-actions
Bot
added
the
meta:needs-changelog
- Created AGENT.md with unified specification (v2.0.0) - Claude config: Deep analysis and architectural recommendations - Copilot config: GitHub-native integration for tour operators - OpenAI config: API automation for configuration workflows - Shared core prompt: Provider-agnostic methodology (284 lines) - Ready for site analysis, architecture recommendations, setup validation - All validations passing Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
- AGENT.md with unified specification (v2.0.0) - Claude, Copilot, OpenAI provider configs - Store analysis, setup optimization, product configuration - Payment integration and performance optimization guidance Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
…dator
Replace stub provider configs with substantial content (1,046 lines):
- shared/core-prompt.md: 7-phase WooCommerce methodology
- claude/{agent.md,tools.json}: 8 tools with full input schemas
- copilot/{agent.md,skills.yaml}: 7 skills with GitHub integration
- openai/{agent.md,tools.json}: 8 functions with parameter schemas
Also documents the 50-option / 50-field limits in docs/ISSUE_FIELDS.md so
the pre-existing validate:issue-fields check passes on develop.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Satisfies changelog-validate (type:feature requires a CHANGELOG.md entry; meta:no-changelog is disallowed for restricted types). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…check Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Add AI Ops standard footer to all woo-config-agent markdown files - Bump ISSUE_FIELDS.md version for freshness validation Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Standardises the Tour Operator Config Agent using the Phase 2 multi-provider pattern: - AGENT.md: Full specification with frontmatter, overview, responsibilities, capabilities, provider support matrix (124 lines) - claude/agent.md: Claude-specific system prompt with domain knowledge and tool descriptions (45+ lines) - claude/tools.json: 5 tools with comprehensive input schemas for tour operator analysis and configuration (215 lines) - copilot/agent.md: Copilot GitHub-native integration guide with skill mappings (60 lines) - copilot/skills.yaml: YAML skill definitions for GitHub Copilot integration (102 lines) - openai/agent.md: OpenAI API-first configuration with function calling strategy (80 lines) - openai/tools.json: 5 functions with full parameter definitions for API integration (291 lines) - shared/core-prompt.md: Provider-agnostic methodology, domain knowledge, safety rules (111 lines) - README.md: Provider support matrix, quick start guide, documentation links (42 lines) Real tour operator domain content covering: single-destination/multi-leg/flexible-date/charter tours, full-upfront/deposit-balance/instalment payment models, multi-currency and multi-gateway payment, booking calendar configuration, customer communication workflows, performance optimisation, and safety-first deployment strategies. All JSON/YAML validates cleanly. Provider implementations ready for multi-provider agent deployment. Closes #1098 Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2bccb60 to
c5e1c5f
Compare
- Fix ISSUE_FIELDS.md version in body (v1.0.9) - Fix UK spelling: optimize → optimise in AGENT.md - Ensure all frontmatter is consistent Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
- Add minItems: 1 to regions array in payment_integrator tool - Ensures required array parameters reject empty arrays - Improves schema validation for OpenAI function calling Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
- Convert setext heading to ATX style (##) - Add blank lines around headings - Remove trailing punctuation from heading Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
…tions - Resolved conflicts in claude/tools.json, openai/tools.json, AGENT.md, and claude/agent.md - Took the detailed 'theirs' version with UK spelling and richer schemas - All JSON files now validate successfully - Removed conflict markers and consolidated duplicate sections Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
…config - Add minItems: 1 validation to regions array in OpenAI tools.json - Update OpenAI model to gpt-4-turbo-2024-04-09 (current supported version) - Add 'Customer & Privacy' column to Copilot project phase_columns - Improves schema validation and Copilot workflow integration Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Ensures frontmatter freshness validation passes by matching today's date. Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
…optimisation) Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
1 participant
Linked issues
Closes #1098
Changelog
Added
Checklist (Global DoD / PR)