chore: upgrade dependencies

.claude/settings.json

@@ -0,0 +1,6 @@
+{
+  "attribution": {
+    "commit": "",
+    "pr": ""
+  }
+}

.github/workflows/publish.yaml

@@ -0,0 +1,29 @@
+name: Publish to crates.io
+
+on:
+  release:
+    types: [published]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Rust
+        uses: dtolnay/rust-toolchain@stable
+
+      - name: Cache cargo
+        uses: Swatinem/rust-cache@v2
+
+      - name: Run tests
+        run: cargo test --verbose
+
+      - name: Publish to crates.io
+        run: cargo publish
+        env:
+          CARGO_REGISTRY_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}

AGENTS.md

@@ -15,10 +15,13 @@ Critical Thinking Fix root cause (not band-aid). Unsure: read more code; if stil
 
 ## Top level requirements
 
-- CLI tool for generating textual artifacts using LLM
-- Uses llm-chain for LLM integration with OpenAI
+- Coding Agent friendly tool to magically generate text and images
+- CLI for generating textual and visual artifacts using LLM
+- Minimal self-contained OpenAI provider (no external LLM libraries)
 - Supports Jinja2-like template variables in prompts
-- Designed for CI/CD integration
+- Model selection and reasoning level configuration
+- Designed for CI/CD integration and AI agent workflows
+- Rich error messages with recovery hints for agent self-correction
 
 ## Local dev expectations
 
@@ -37,11 +40,19 @@ src/
 ├── output.rs         # JSON output utilities
 ├── commands/
 │   ├── mod.rs        # Command traits (CommandExec, CommandResult)
-│   └── generate.rs   # Generate command implementation
+│   ├── generate.rs   # Generate command implementation
+│   └── image.rs      # Image generation command implementation
+├── provider/
+│   ├── mod.rs        # Provider abstraction types (Chat + Responses API)
+│   └── openai.rs     # OpenAI provider implementation
 └── trickery/
     ├── mod.rs
-    └── generate.rs   # LLM template generation logic
+    ├── generate.rs   # LLM template generation logic
+    └── image.rs      # Image generation logic
 prompts/              # Example prompt templates
+test_cases/           # Test case templates for generate command
+specs/                # Feature specifications
+docs/                 # Feature documentation
 ```
 
 ## Naming
@@ -63,6 +74,13 @@ CI is implemented using GitHub Actions (`.github/workflows/ci.yaml`):
 2. Linting: Run `cargo clippy` and fix warnings
 3. Tests: Ensure `cargo test` passes
 4. Build: Ensure `cargo build` succeeds
+5. Full help: If CLI options changed, update `print_full_help()` in `src/main.rs`
+6. Lockfile: Run `cargo update --workspace` after version bumps or dependency changes to sync Cargo.lock
+7. README: If README needs changes, update `prompts/trickery_readme.md` and regenerate with `trickery generate ./prompts/trickery_readme.md > README.md`
+
+## Attribution
+
+NEVER add links to Claude sessions in PR body or commits. Also never attribute commit or merge commit to coding agents, always use real user.
 
 ## Commit message conventions
 
@@ -102,3 +120,48 @@ High-level approach.
 - [ ] Smoke tests are passed
 - [ ] Documentation is updated
 ```
+
+## Specs
+
+`specs/` folder contains feature specifications outlining requirements for specific features and components. New code should comply with these specifications or propose changes to them.
+
+Available specs:
+
+- `coding-agent-design.md` - Agent-friendly design principles, error recovery, discoverability
+- `llm-provider.md` - LLM provider abstraction, OpenAI integration, design choices
+- `text-input.md` - Direct text input via --text option, alternative to file input
+
+Specification format: Abstract and Requirements sections.
+
+## Test Cases
+
+`test_cases/` folder contains manual smoke test cases for validating CLI functionality. Run these after changes to verify behavior.
+
+Available test cases:
+
+- `basic_generation.md` - Simple prompt generation without variables
+- `template_variables.md` - Jinja2-style variable substitution
+- `json_output.md` - JSON output format flag
+- `image_multimodal.md` - Image input for multimodal prompts
+- `image_generate.md` - Image generation and editing command
+- `error_handling.md` - Error scenarios and messages
+- `text_input.md` - Direct text input via --text option
+
+### Test case template
+
+```markdown
+# Test: <Name>
+
+## Abstract
+<One sentence describing what this test validates>
+
+## Prerequisites
+- `cargo install --path .`
+- <Other required setup, env vars, files>
+
+## Steps
+
+### 1. <Step name>
+**Run:** `trickery <command>`
+**Expect:** <Expected outcome>
+```