Add AI agent configs, issue templates, and update contributing guide

- AGENTS.md, .github/copilot-instructions.md for AI agent support
- notify-workspaces.yml to dispatch API updates to autolens_workspace
- Issue templates for feature requests and bug reports
- CONTRIBUTING.md updated with AI-first workflow and code example guidance

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: 2 people

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,40 @@
+---
+name: Bug Report
+about: Report a bug or unexpected behaviour
+title: 'fix: '
+labels: bug
+assignees: ''
+---
+
+## Description
+
+<!-- Clear description of the bug -->
+
+## Steps to Reproduce
+
+1. 
+2. 
+3. 
+
+## Expected Behaviour
+
+<!-- What should happen -->
+
+## Actual Behaviour
+
+<!-- What actually happens -->
+
+## Environment
+
+- OS: 
+- Python version: 
+- Package version: 
+
+## Original Prompt
+
+<details>
+<summary>Click to expand starting prompt</summary>
+
+<!-- If this issue was created from an AI prompt, paste the original prompt here -->
+
+</details>

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,51 @@
+---
+name: Feature / Task Request
+about: Propose a new feature, improvement, or task
+title: ''
+labels: enhancement
+assignees: ''
+---
+
+## Overview
+
+<!-- 2-4 sentence summary of what this task is and why it matters -->
+
+## Plan
+
+<!-- High-level bullet-point plan, human readable, no code -->
+
+<details>
+<summary>Detailed implementation plan</summary>
+
+### Affected Repositories
+<!-- List repos this touches, mark primary -->
+
+### Implementation Steps
+<!-- Step-by-step with file paths and specifics -->
+
+### Key Files
+<!-- List files that will be modified -->
+
+</details>
+
+## Example Code
+
+<!-- If your feature involves a specific calculation, algorithm, or small piece of functionality,
+     include example code here. Even a rough script, a working prototype, or a snippet showing
+     the existing behaviour you want changed helps enormously.
+
+     Code gives AI agents and human contributors concrete context and dramatically reduces
+     misunderstandings. Delete this section if not applicable. -->
+
+```python
+# Paste your example code here
+```
+
+## Original Prompt
+
+<details>
+<summary>Click to expand starting prompt</summary>
+
+<!-- If this issue was created from an AI prompt, paste the original prompt here -->
+
+</details>

.github/copilot-instructions.md

@@ -0,0 +1,27 @@
+# Copilot Coding Agent Instructions
+
+You are working on **PyAutoLens**, a Python library for strong gravitational lens modeling built on PyAutoGalaxy.
+
+## Key Rules
+
+- Run tests after every change: `python -m pytest test_autolens/`
+- Format code with `black autolens/`
+- All files must use Unix line endings (LF, `\n`)
+- Decorated functions (`@to_array`, `@to_grid`, `@to_vector_yx`) must return **raw arrays**, not autoarray wrappers
+- The `xp` parameter controls NumPy (`xp=np`) vs JAX (`xp=jnp`) — never import JAX at module level
+- Functions called inside `jax.jit` must guard autoarray wrapping with `if xp is np:`
+- If changing public API, clearly document what changed in your PR description — downstream workspaces depend on this
+
+## Architecture
+
+- `autolens/lens/` — `Tracer`, multi-plane ray-tracing, deflection logic
+- `autolens/imaging/`, `interferometer/`, `point/` — Dataset-specific fit and analysis classes
+- `autolens/plot/` — Visualisation for all data types
+- `autolens/aggregator/` — Results scraping
+- `test_autolens/` — Test suite
+
+## Sandboxed runs
+
+```bash
+NUMBA_CACHE_DIR=/tmp/numba_cache MPLCONFIGDIR=/tmp/matplotlib python -m pytest test_autolens/
+```

.github/workflows/notify-workspaces.yml

@@ -0,0 +1,37 @@
+# Notify downstream workspaces when a PR is merged to main.
+#
+# Sends a repository_dispatch event to each workspace repo so they can
+# trigger an automated API update (via Copilot coding agent or similar).
+#
+# Required secret:
+#   WORKSPACE_DISPATCH_TOKEN — PAT with repo scope on the target workspace
+#                              repositories.
+
+name: Notify Workspaces
+
+on:
+  pull_request:
+    types: [closed]
+    branches: [main]
+
+jobs:
+  dispatch:
+    if: github.event.pull_request.merged == true
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        workspace:
+          - Jammy2211/autolens_workspace
+    steps:
+      - name: Send repository_dispatch
+        env:
+          GH_TOKEN: ${{ secrets.WORKSPACE_DISPATCH_TOKEN }}
+        run: |
+          gh api --method POST \
+            -H "Accept: application/vnd.github+json" \
+            "/repos/${{ matrix.workspace }}/dispatches" \
+            -f "event_type=api-update" \
+            -f "client_payload[pr_number]=${{ github.event.pull_request.number }}" \
+            -f "client_payload[pr_title]=${{ github.event.pull_request.title }}" \
+            -f "client_payload[pr_branch]=${{ github.event.pull_request.head.ref }}" \
+            -f "client_payload[pr_url]=${{ github.event.pull_request.html_url }}"

AGENTS.md

@@ -0,0 +1,52 @@
+# PyAutoLens — Agent Instructions
+
+**PyAutoLens** is a Python library for strong gravitational lens modeling, built on PyAutoGalaxy. It adds multi-plane ray-tracing via the `Tracer` object and lensing-specific fit/analysis classes.
+
+## Setup
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Running Tests
+
+```bash
+python -m pytest test_autolens/
+python -m pytest test_autolens/lens/test_tracer.py
+python -m pytest test_autolens/imaging/test_fit_imaging.py -s
+```
+
+### Sandboxed / Codex runs
+
+```bash
+NUMBA_CACHE_DIR=/tmp/numba_cache MPLCONFIGDIR=/tmp/matplotlib python -m pytest test_autolens/
+```
+
+## Key Architecture
+
+- **Tracer** (`lens/tracer.py`): groups galaxies by redshift plane, performs multi-plane ray-tracing
+- **Fit classes**: `FitImaging`, `FitInterferometer`, `FitPointDataset` — extend autogalaxy equivalents with lensing
+- **Analysis classes**: `AnalysisImaging`, `AnalysisInterferometer`, `AnalysisPoint`
+- **Namespace**: `al.mp.*` (mass), `al.lp.*` (light), `al.Galaxy`, `al.Tracer`
+
+## Dependencies
+
+- `autogalaxy` — galaxy morphology, profiles, single-plane fitting
+- `autoarray` — data structures, grids, masks, inversions
+- `autofit` — non-linear search and model-fitting framework
+
+## Key Rules
+
+- The `xp` parameter controls NumPy vs JAX: `xp=np` (default) or `xp=jnp`
+- Functions inside `jax.jit` must guard autoarray wrapping with `if xp is np:`
+- Decorated functions return **raw arrays** — the decorator wraps them
+- All files must use Unix line endings (LF)
+- Format with `black autolens/`
+
+## Working on Issues
+
+1. Read the issue description and any linked plan.
+2. Identify affected files and write your changes.
+3. Run the full test suite: `python -m pytest test_autolens/`
+4. Ensure all tests pass before opening a PR.
+5. If changing public API, note the change in your PR description — downstream workspaces may need updates.

CONTRIBUTING.md

@@ -1,3 +1,34 @@
+# AI-Assisted Development
+
+This project uses an AI-first development workflow. Most features, bug fixes, and improvements are implemented through AI coding agents (Claude Code, GitHub Copilot, OpenAI Codex) working from structured issue descriptions.
+
+## How It Works
+
+1. **Issues are the starting point** — Every task begins as a GitHub issue with a structured format: an overview, a human-readable plan, a detailed implementation plan (in a collapsible block), and optionally the original prompt that generated the issue.
+
+2. **AI agents pick up issues** — Issues can be assigned to AI coding agents (e.g. GitHub Copilot) which read the issue description, `AGENTS.md`, and `CLAUDE.md` for context, then implement the changes autonomously.
+
+3. **Human review** — All AI-generated pull requests are reviewed by maintainers before merging.
+
+## Creating an Issue
+
+When opening an issue, please use the provided issue templates. The **Feature / Task Request** template follows our standard format:
+
+- **Overview** — What and why, in 2-4 sentences
+- **Plan** — High-level bullet points (human-readable)
+- **Detailed implementation plan** — File paths, steps, key files (in a collapsible block)
+- **Original Prompt** — If you used an AI to help draft the issue, include the original prompt
+
+If your feature involves a specific calculation, algorithm, or small piece of functionality — **include example code**. Even a rough script, a working prototype, or a snippet showing the existing behaviour you want to change makes a huge difference. Code examples give AI agents and human contributors concrete context to work from, and dramatically reduce misunderstandings about what you're asking for.
+
+This structure ensures that both human contributors and AI agents can understand and act on the issue effectively.
+
+## Contributing Without AI
+
+Traditional contributions are equally welcome! If you prefer to work without AI tools, simply follow the development setup and pull request guidelines below. The issue templates are helpful for any contributor, AI or human.
+
+---
+
 ## Community Guidelines
 
 We strive to maintain a welcoming, respectful, and inclusive community. All contributors—whether opening issues, submitting pull requests, reviewing code, or participating in discussions—are expected to follow these guidelines.