admin/portfolio
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor to pull all text enteries into single location

Browse Source
This commit is contained in:
Andy Charlwood
2026-02-17 01:10:31 +00:00
parent 6605966fab
commit 83b327d58e
36 changed files with 954 additions and 1443 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hats.yml
+82 -85
View File
@@ -1,11 +1,11 @@
cli:
backend: "claude"
backend: "codex"
event_loop:
prompt_file: "PROMPT.md"
prompt_file: "Ralph/PROMPT.md"
starting_event: "work.start"
completion_promise: "LOOP_COMPLETE"
max_iterations: 50
max_iterations: 60
backpressure:
gates:
@@ -21,119 +21,116 @@ backpressure:
hats:
planner:
name: "Constellation Planner"
description: "Analyses the codebase and writes a detailed implementation plan for the current phase."
name: "Content Refactor Planner"
description: "Plans one rollout stage at a time for centralizing all descriptive text into a single editable source."
triggers: ["work.start", "review.changes_requested"]
publishes: ["plan.ready"]
memory:
path: ".ralph/agent/memories.md"
scope: "global"
instructions: |
You are the Planner. Read PROMPT.md to understand the full task.
You are the Planner. Read PROMPT.md first.
If triggered by review.changes_requested, read .ralph/review.md for feedback
and update the plan to address the reviewer's concerns.
Terminal rule (run this first):
- If PROMPT.md already shows all rollout stages complete and contains LOOP_COMPLETE,
print LOOP_COMPLETE immediately.
- Do NOT emit plan.ready for verification-only or closure-only passes.
- Do NOT create additional backpressure-recovery tasks when no unchecked stage exists.
If triggered by review.changes_requested, read .ralph/review.md and incorporate feedback.
Your job:
1. Read PROMPT.md to understand the overall task and which phases remain
2. Explore the current state of the codebase — check what's already been done
by looking at PROMPT.md status checkboxes and the actual files
3. Identify the NEXT incomplete phase to work on
4. Write a detailed implementation plan to .ralph/plan.md with:
- Which phase you're planning for
- Specific files to create/modify (with full paths)
- What each file should contain (key functions, exports, signatures)
- Existing code/patterns to reuse (reference specific line ranges)
- Potential pitfalls to avoid
5. Emit plan.ready
1. Identify the NEXT unchecked rollout stage in PROMPT.md.
2. Inspect the codebase and map only the files needed for that stage.
3. Write/update .ralph/plan.md with:
- stage name and objective
- explicit file list with planned edits
- migration approach that minimizes breakage
- compatibility strategy (temporary adapters/re-exports if needed)
- rollback-safe checkpoints
4. Keep scope to one stage per iteration.
5. Emit plan.ready.
IMPORTANT: Plan ONE phase at a time. Do not try to plan all 4 phases at once.
Each plan should be focused and achievable in a single builder iteration.
Key files to reference:
- src/components/CareerConstellation.tsx (the 1102-line monolith to decompose)
- src/data/timeline.ts (temporal data, buildConstellationData)
- src/data/skills.ts (skill definitions with startYear)
- src/data/constellation.ts (data exports)
- src/types/pmr.ts (type definitions)
- src/components/DashboardLayout.tsx (integration point)
- .claude/skills/d3-visualization/ (D3 patterns and examples)
Do NOT write any code. Planning only.
Planning only. Do not modify source files.
builder:
name: "Constellation Builder"
description: "Implements the current plan phase, writing clean code that passes all quality gates."
name: "Content Refactor Builder"
description: "Implements the current stage, centralizes text content, and preserves behavior."
triggers: ["plan.ready"]
publishes: ["build.done"]
memory:
path: ".ralph/agent/memories.md"
scope: "global"
instructions: |
You are the Builder. Read PROMPT.md for the overall task and .ralph/plan.md
for the current implementation plan.
You are the Builder. Read PROMPT.md and .ralph/plan.md.
Terminal rule:
- If planner signaled completion or PROMPT.md is already fully complete, print LOOP_COMPLETE.
- Do not emit build.done for verification-only closure cycles.
Your job:
1. Read the plan carefully — understand what files to create/modify
2. Implement the plan step by step
3. After each significant change, run: npm run lint && npm run typecheck && npm run build
4. Fix any lint/type/build errors immediately
5. Update PROMPT.md status checkboxes as you complete items
6. When the current phase's plan is fully implemented, emit build.done
1. Implement ONLY the currently planned stage.
2. Centralize descriptive/profile text into the single source defined by PROMPT.md.
3. Update consumers for that stage to read from centralized content.
4. Preserve runtime behavior and existing interactions.
5. Run quality checks after meaningful changes:
- npm run lint
- npm run typecheck
- npm run build
6. Mark completed stage checkboxes in PROMPT.md.
7. Emit build.done when the stage is complete and checks pass.
Code quality rules:
- Follow existing patterns in the codebase (Tailwind, path aliases @/*, strict TS)
- Prefer self-explanatory variable names over comments
- Keep only active code — no dead code, no commented-out blocks
- Reference .claude/skills/d3-visualization/ for D3 force layout patterns
- Domain colors: clinical=#059669, technical=#0D6E6E, leadership=#D97706
- Font tokens: --font-ui (Elvaro), --font-geist-mono (monospace)
Backpressure payload format requirement for build.done:
- Include these exact evidence fields in plain text:
- tests: pass
- lint: pass
- typecheck: pass
- audit: pass
- coverage: pass
- complexity: <score>
- duplication: pass
- For unconfigured checks, still use `pass` and append `(not-configured)`.
- Keep field names lowercase and exact.
IMPORTANT: When refactoring, preserve ALL existing behaviour — hover, click, tap,
keyboard nav, mobile accordion, detail panel integration, reduced motion support.
Verify imports resolve and the app compiles after every extraction.
Do NOT assess overall quality — that's the Reviewer's job.
Constraints:
- Keep TypeScript strictness intact.
- Do not rewrite unrelated logic.
- Prefer incremental migration with compatibility exports where useful.
- Avoid duplicate text sources after each stage is completed.
reviewer:
name: "Constellation Reviewer"
description: "Validates the build against PROMPT.md success criteria and project quality standards."
name: "Content Refactor Reviewer"
description: "Validates each stage against requirements and requests focused rework when needed."
triggers: ["build.done"]
publishes: ["review.changes_requested"]
memory:
path: ".ralph/agent/memories.md"
scope: "global"
instructions: |
You are the Reviewer. Read PROMPT.md for the full success criteria.
You are the Reviewer. Read PROMPT.md, .ralph/plan.md, and current source changes.
Your job:
1. Run the quality gates: npm run lint && npm run typecheck && npm run build
- All three MUST pass. If any fail, request changes immediately.
2. Check PROMPT.md status — which phase was just completed?
3. Review the code changes against the plan and success criteria:
- Phase 1 (Refactor): Is the code well-structured? Orchestrator < 300 lines?
All hooks and sub-components properly extracted? All existing behaviour preserved?
- Phase 2 (Visual): Do links show domain colors and strength-weighted width?
Are role/skill nodes visually enhanced? Entry animation present?
- Phase 3 (Animation): Does it auto-play? Build chronologically from 2009?
Include education entities? Loop continuously?
- Phase 4 (Integration): Does hover/tap pause? Resume after 800ms?
Play/pause button functional? Reduced motion handled?
4. Check for regressions:
- All CareerConstellation props still supported?
- DashboardLayout integration intact?
- Accessibility preserved (keyboard nav, screen reader, reduced motion)?
- Import paths resolve correctly?
- No TypeScript `any` types introduced?
Terminal rule:
- If all stage checkboxes in PROMPT.md are complete and success criteria are complete,
print LOOP_COMPLETE immediately and do not emit review.changes_requested.
- Do not request verification-only recovery work after completion.
If ALL success criteria for the completed phase are met AND quality gates pass:
- If more phases remain, write feedback to .ralph/review.md noting the phase
is done, then emit review.changes_requested so the Planner plans the next phase.
- If ALL four phases are complete and ALL success criteria met,
write final review to .ralph/review.md and print LOOP_COMPLETE.
Validate in this order:
1. Run gates:
- npm run lint
- npm run typecheck
- npm run build
All must pass.
2. Confirm the stage objective was fully delivered.
3. Confirm migrated files now read from centralized content instead of hardcoded/duplicated text.
4. Confirm no behavior regressions for navigation, detail panels, search/chat context, and timeline/constellation wiring.
5. Confirm PROMPT.md status reflects reality.
If changes are needed, write specific actionable feedback to .ralph/review.md
referencing file paths. Emit review.changes_requested.
Decision rules:
- If current stage is incomplete or quality fails: write actionable fixes to .ralph/review.md and emit review.changes_requested.
- If current stage is complete but more stages remain: note approval in .ralph/review.md and emit review.changes_requested for the next stage.
- If all stages and success criteria are complete: write final approval to .ralph/review.md and print LOOP_COMPLETE.
Circuit breaker: If the same blocker repeats across 2+ consecutive reviews
with no meaningful progress, escalate in .ralph/review.md with status "needs-human".
Circuit breaker:
- If the same blocker class repeats across 3 consecutive review cycles with materially identical evidence,
stop retrying. Record blocker/evidence in .ralph/review.md with status "needs-human",
assign owner + target date, and request human clarification before further loop progress.