aia 0.11.1 → 1.0.0.pre.alpha

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dac8dfbee13b2a4c8276f7052653f4b664bd1cfb5ce036aab66e233cb4f2bcd3
-  data.tar.gz: 9d35cdfdad9dc3f8a673428bc78747f2a63323153e5eb2b7049c819594a8c1da
+  metadata.gz: 79adae0e7c376a4b6aceab36d1378322ac8d35f3a716ec55f165744ebe7e901a
+  data.tar.gz: 0f8bc3fc75d717c1833ee13b9d37b447f674cc178d1c80e4367ec5781333f97b
 SHA512:
-  metadata.gz: 6591e945b857bc8ea91afdc0efbb1ab118e1f91a829a6fe3a1de753bf2b93effee9ce6f48dc176caa8213376bf483fe7f039ee8c64916c4031d2a1cf81695951
-  data.tar.gz: 3976784e41ce2673dfab51da5dbbc927e636ab376c87c443571b26a94242739d46bcab6fed4d9d268662aed786d9a325d512701c353d164a0c34363767ebd73a
+  metadata.gz: 880eb80b2670139b80461bd62e45f393072cea612f3067d8799c79ceceb60f5ac862e1527e6d6856bf7c8841140dc14c04621db0e282cb70c6a1b4a4ee13fdfc
+  data.tar.gz: 3b345422fa6aab72da7a3baa28b347720a3fed7999b807da9b350a28459d6e64daa0f7bcdc731da8446c56929a3010518cfec17cc6a06c04bf28a4ea0e05e74e

data/.version

@@ -1 +1 @@
-0.11.1
+1.0.0-alpha

data/CHANGELOG.md

@@ -1,4 +1,21 @@
 # Changelog
+## [0.11.1] - 2026-02-03
+
+### New Features
+- **`bin/migrate_prompts` Script**: Standalone Ruby script for migrating prompt files from prompt_manager v0.5.8 format to v1.0.0 format
+  - Converts `.txt` + `.json` files to `.md` with YAML front matter and ERB parameters
+  - Placeholder conversion: `[PLACEHOLDER]` → `<%= placeholder %>`
+  - Space placeholder normalization: `[TECH STACK]` → `<%= tech_stack %>`
+  - Directive migration: `//config`, `//temp`, `//topp`, `//include`, `//shell`, `//ruby`, `//backend`, `//next`, `//pipeline`
+  - Comment conversion: `#` lines → HTML comments (preserves comments inside code fences and ERB blocks)
+  - Code fence detection: files containing ``` fences are flagged as `.txt-review` for manual review
+  - JSON history file migration: `.json` parameter history converted to YAML `parameters:` block in front matter
+  - `--reprocess` option to re-examine `.txt-review` files and recover those that now process cleanly
+  - `--dry-run` mode for safe previewing of changes
+  - `--verbose` logging with detailed per-file output
+  - `--force` to overwrite existing `.md` files
+  - Supports both directory scanning and specific file arguments
+
 ## [0.11.0] - 2026-02-02
 
 ### New Features

data/README.md

@@ -25,7 +25,7 @@ AIA is a command-line utility that facilitates interaction with AI models throug
 
 AIA leverages the following Ruby gems:
 
-- **[prompt_manager](https://github.com/madbomber/prompt_manager)** to manage prompts,
+- **[pm](https://github.com/madbomber/prompt_manager)** to manage prompts,
 - **[ruby_llm](https://rubyllm.com)** to access LLM providers,
 - **[ruby_llm-mcp](https://www.rubyllm-mcp.com)** for Model Context Protocol (MCP) support,
 - and can use the **[shared_tools gem](https://github.com/madbomber/shared_tools)** which provides a collection of common ready-to-use MCP clients and functions for use with LLMs that support tools.
@@ -50,7 +50,7 @@ For more information on AIA visit these locations:
 3. **Create your first prompt:**
    ```bash
    mkdir -p ~/.prompts
-   echo "What is [TOPIC]?" > ~/.prompts/what_is.txt
+   echo "What is [TOPIC]?" > ~/.prompts/what_is.md
    ```
 
 4. **Run your prompt:**
@@ -278,11 +278,11 @@ aia --fuzzy
 
 ```
 ~/.prompts/              # Default prompts directory
-├── ask.txt             # Simple question prompt
-├── code_review.txt     # Code review prompt
+├── ask.md              # Simple question prompt
+├── code_review.md      # Code review prompt
 ├── roles/              # Role/system prompts
-│   ├── expert.txt      # Expert role
-│   └── teacher.txt     # Teaching role
+│   ├── expert.md       # Expert role
+│   └── teacher.md      # Teaching role
 └── _prompts.log        # History log
 ```
 
@@ -304,7 +304,7 @@ The most commonly used configuration options:
 
 AIA determines configuration settings using this order (highest to lowest priority):
 
-1. **Embedded config directives** (in prompt files): `//config model = gpt-4`
+1. **Embedded config directives** (in prompt files): `/config model = gpt-4`
 2. **Command-line arguments**: `--model gpt-4`
 3. **Environment variables**: `export AIA_MODEL=gpt-4`
 4. **Configuration files**: `~/.aia/config.yml`
@@ -329,8 +329,8 @@ chat: false
 
 **Embedded Directives** (in prompt files):
 ```
-//config model = gpt-4
-//config temperature = 0.8
+/config model = gpt-4
+/config temperature = 0.8
 
 Your prompt content here...
 ```
@@ -365,7 +365,7 @@ Your prompt content here...
 | parameter_regex | --regex | '(?-mix:(\[[A-Z _\|]+\]))' | AIA_PROMPTS__PARAMETER_REGEX |
 | pipeline | --pipeline | [] | AIA_PIPELINE |
 | presence_penalty | --presence-penalty | 0.0 | AIA_LLM__PRESENCE_PENALTY |
-| prompt_extname | | .txt | AIA_PROMPTS__EXTNAME |
+| prompt_extname | | .md | AIA_PROMPTS__EXTNAME |
 | prompts_dir | --prompts-dir | ~/.prompts | AIA_PROMPTS__DIR |
 | refresh | --refresh | 7 (days) | AIA_REGISTRY__REFRESH |
 | require_libs | --rq --require | [] | AIA_REQUIRE_LIBS |
@@ -397,27 +397,27 @@ Your prompt content here...
 
 ### Prompt Directives
 
-Directives are special commands in prompt files that begin with `//` and provide dynamic functionality:
+Directives are special commands in prompt files that begin with `/` and provide dynamic functionality:
 
 | Directive | Description | Example |
 |-----------|-------------|---------|
-| `//config` | Set configuration values | `//config model = gpt-4` |
-| `//context` | Show context for this conversation with checkpoint markers | `//context` |
-| `//checkpoint` | Create a named checkpoint of current context | `//checkpoint save_point` |
-| `//restore` | Restore context to a previous checkpoint | `//restore save_point` |
-| `//include` | Insert file contents | `//include path/to/file.txt` |
-| `//paste` | Insert clipboard contents | `//paste` |
-| `//shell` | Execute shell commands | `//shell ls -la` |
-| `//robot` | Show the pet robot ASCII art w/versions | `//robot` |
-| `//ruby` | Execute Ruby code | `//ruby puts "Hello World"` |
-| `//next` | Set next prompt in sequence | `//next summary` |
-| `//pipeline` | Set prompt workflow | `//pipeline analyze,summarize,report` |
-| `//clear` | Clear conversation history | `//clear` |
-| `//help` | Show available directives | `//help` |
-| `//model` | Show current model configuration | `//model` |
-| `//available_models` | List available models | `//available_models` |
-| `//tools` | Show available tools (optional filter by name) | `//tools` or `//tools file` |
-| `//review` | Review current context with checkpoint markers | `//review` |
+| `/config` | Set configuration values | `/config model = gpt-4` |
+| `/context` | Show context for this conversation with checkpoint markers | `/context` |
+| `/checkpoint` | Create a named checkpoint of current context | `/checkpoint save_point` |
+| `/restore` | Restore context to a previous checkpoint | `/restore save_point` |
+| `/include` | Insert file contents | `/include path/to/file.txt` |
+| `/paste` | Insert clipboard contents | `/paste` |
+| `/shell` | Execute shell commands | `/shell ls -la` |
+| `/robot` | Show the pet robot ASCII art w/versions | `/robot` |
+| `/ruby` | Execute Ruby code | `/ruby puts "Hello World"` |
+| `/next` | Set next prompt in sequence | `/next summary` |
+| `/pipeline` | Set prompt workflow | `/pipeline analyze,summarize,report` |
+| `/clear` | Clear conversation history | `/clear` |
+| `/help` | Show available directives | `/help` |
+| `/model` | Show current model configuration | `/model` |
+| `/available_models` | List available models | `/available_models` |
+| `/tools` | Show available tools (optional filter by name) | `/tools` or `/tools file` |
+| `/review` | Review current context with checkpoint markers | `/review` |
 
 Directives can also be used in the interactive chat sessions.
 
@@ -425,12 +425,12 @@ Directives can also be used in the interactive chat sessions.
 
 ```bash
 # Set model and temperature for this prompt
-//config model = gpt-4
-//config temperature = 0.9
+/config model = gpt-4
+/config temperature = 0.9
 
 # Enable chat mode and terse responses
-//config chat = true
-//config terse = true
+/config chat = true
+/config terse = true
 
 Your prompt content here...
 ```
@@ -439,16 +439,16 @@ Your prompt content here...
 
 ```bash
 # Include file contents
-//include ~/project/README.md
+/include ~/project/README.md
 
 # Paste clipboard contents
-//paste
+/paste
 
 # Execute shell commands
-//shell git log --oneline -10
+/shell git log --oneline -10
 
 # Run Ruby code
-//ruby require 'json'; puts JSON.pretty_generate({status: "ready"})
+/ruby require 'json'; puts JSON.pretty_generate({status: "ready"})
 
 Analyze the above information and provide insights.
 ```
@@ -459,19 +459,19 @@ AIA provides powerful context management capabilities in chat mode through check
 
 ```bash
 # Create a checkpoint with automatic naming (1, 2, 3...)
-//checkpoint
+/checkpoint
 
 # Create a named checkpoint
-//checkpoint important_decision
+/checkpoint important_decision
 
 # Restore to the last checkpoint
-//restore
+/restore
 
 # Restore to a specific checkpoint
-//restore important_decision
+/restore important_decision
 
 # View context with checkpoint markers
-//context
+/context
 ```
 
 **Example Chat Session:**
@@ -479,17 +479,17 @@ AIA provides powerful context management capabilities in chat mode through check
 You: Tell me about Ruby programming
 AI: Ruby is a dynamic programming language...
 
-You: //checkpoint ruby_basics
+You: /checkpoint ruby_basics
 
 You: Now explain object-oriented programming
 AI: Object-oriented programming (OOP) is...
 
-You: //checkpoint oop_concepts
+You: /checkpoint oop_concepts
 
 You: Actually, let's go back to Ruby basics
-You: //restore ruby_basics
+You: /restore ruby_basics
 
-You: //context
+You: /context
 === Chat Context ===
 Total messages: 4
 Checkpoints: ruby_basics, oop_concepts
@@ -506,10 +506,10 @@ Checkpoints: ruby_basics, oop_concepts
 
 **Key Features:**
 - **Auto-naming**: Checkpoints without names use incrementing integers (1, 2, 3...)
-- **Named checkpoints**: Use meaningful names like `//checkpoint before_refactor`
-- **Default restore**: `//restore` without a name restores to the last checkpoint
-- **Context visualization**: `//context` shows checkpoint markers in conversation history
-- **Clean slate**: `//clear` removes all context and checkpoints
+- **Named checkpoints**: Use meaningful names like `/checkpoint before_refactor`
+- **Default restore**: `/restore` without a name restores to the last checkpoint
+- **Context visualization**: `/context` shows checkpoint markers in conversation history
+- **Clean slate**: `/clear` removes all context and checkpoints
 
 #### Custom Directive Examples
 
@@ -535,7 +535,7 @@ end
 aia --tools examples/directives/ask.rb --chat
 
 # Use the results of the custom directive as input to a prompt
-//ask gather the latest closing data for the DOW, NASDAQ, and S&P 500
+/ask gather the latest closing data for the DOW, NASDAQ, and S&P 500
 ```
 
 ### Multi-Model Support
@@ -602,11 +602,11 @@ Response from the third model...
 
 #### Model Information
 
-View your current multi-model configuration using the `//model` directive:
+View your current multi-model configuration using the `/model` directive:
 
 ```bash
 # In any prompt file or chat session
-//model
+/model
 ```
 
 **Example Output:**
@@ -722,11 +722,11 @@ export LMS_API_BASE=http://localhost:1234/v1
 
 #### Listing Local Models
 
-The `//models` directive automatically detects local providers and queries their endpoints:
+The `/models` directive automatically detects local providers and queries their endpoints:
 
 ```bash
 # In a prompt file or chat session
-//models
+/models
 
 # Output will show:
 # - Ollama models from http://localhost:11434/api/tags
@@ -792,8 +792,8 @@ Chain multiple prompts for complex workflows:
 aia analyze --next summarize --next report
 
 # In prompt files
-# analyze.txt contains: //next summarize
-# summarize.txt contains: //next report
+# analyze.md contains: /next summarize
+# summarize.md contains: /next report
 ```
 
 #### Using --pipeline
@@ -803,31 +803,31 @@ aia analyze --next summarize --next report
 aia research --pipeline analyze,summarize,report,present
 
 # In prompt file
-//pipeline analyze,summarize,report,present
+/pipeline analyze,summarize,report,present
 ```
 
 #### Example Workflow
 
-**research.txt:**
+**research.md:**
 ```
-//config model = gpt-4
-//next analyze
+/config model = gpt-4
+/next analyze
 
 Research the topic: [RESEARCH_TOPIC]
 Provide comprehensive background information.
 ```
 
-**analyze.txt:**
+**analyze.md:**
 ```
-//config output = analysis.md
-//next summarize
+/config output = analysis.md
+/next summarize
 
 Analyze the research data and identify key insights.
 ```
 
-**summarize.txt:**
+**summarize.md:**
 ```
-//config output = summary.md
+/config output = summary.md
 
 Create a concise summary of the analysis with actionable recommendations.
 ```
@@ -841,7 +841,7 @@ Roles define the context and personality for AI responses:
 aia --role expert analyze_code.rb
 
 # Roles are stored in ~/.prompts/roles/
-# expert.txt might contain:
+# expert.md might contain:
 # "You are a senior software engineer with 15 years of experience..."
 ```
 
@@ -849,7 +849,7 @@ aia --role expert analyze_code.rb
 
 ```bash
 # Create a code reviewer role
-cat > ~/.prompts/roles/code_reviewer.txt << EOF
+cat > ~/.prompts/roles/code_reviewer.md << EOF
 You are an experienced code reviewer. Focus on:
 - Code quality and best practices
 - Security vulnerabilities
@@ -928,7 +928,7 @@ Roles can be organized in subdirectories:
 ```bash
 # Create nested role structure
 mkdir -p ~/.prompts/roles/specialized
-echo "You are a senior software architect..." > ~/.prompts/roles/specialized/senior_architect.txt
+echo "You are a senior software architect..." > ~/.prompts/roles/specialized/senior_architect.md
 
 # Use nested roles
 aia --model gpt-4o=specialized/senior_architect design.md
@@ -1144,11 +1144,11 @@ When MCP servers are configured, AIA displays them in the startup robot:
   (\   /____\
 ```
 
-Use the `//tools` directive in chat mode to see all available tools including those from MCP servers:
+Use the `/tools` directive in chat mode to see all available tools including those from MCP servers:
 
 ```bash
 aia --chat
-> //tools
+> /tools
 
 Available Tools:
 - github_create_issue: Create a new GitHub issue
@@ -1158,7 +1158,7 @@ Available Tools:
 ...
 
 # Filter tools by name (case-insensitive)
-> //tools github
+> /tools github
 
 Available Tools (filtered by 'github')
 - github_create_issue: Create a new GitHub issue
@@ -1206,7 +1206,7 @@ aia --require shared_tools/ruby_llm/edit_file --chat
 aia --require shared_tools/ruby_llm --tools ~/my-tools/ --chat
 ```
 
-The above examples show the shared_tools being used within an interactive chat session.  They are also available in batch prompts as well using the same --require option.  You can also use the //ruby directive to require the shared_tools as well and using a require statement within an ERB block.
+The above examples show the shared_tools being used within an interactive chat session.  They are also available in batch prompts as well using the same --require option.  You can also use the /ruby directive to require the shared_tools as well and using a require statement within an ERB block.
 
 ## Examples & Tips
 
@@ -1214,9 +1214,9 @@ The above examples show the shared_tools being used within an interactive chat s
 
 #### Code Review Prompt
 ```bash
-# ~/.prompts/code_review.txt
-//config model = gpt-4o-mini
-//config temperature = 0.3
+# ~/.prompts/code_review.md
+/config model = gpt-4o-mini
+/config temperature = 0.3
 
 Review this code for:
 - Best practices adherence
@@ -1231,21 +1231,21 @@ Usage: `aia code_review mycode.rb`
 
 #### Meeting Notes Processor
 ```bash
-# ~/.prompts/meeting_notes.txt
-//config model = gpt-4o-mini
-//pipeline format,action_items
+# ~/.prompts/meeting_notes.md
+/config model = gpt-4o-mini
+/pipeline format,action_items
 
 Raw meeting notes:
-//include [NOTES_FILE]
+/include [NOTES_FILE]
 
 Please clean up and structure these meeting notes.
 ```
 
 #### Documentation Generator
 ```bash
-# ~/.prompts/document.txt
-//config model = gpt-4o-mini
-//shell find [PROJECT_DIR] -name "*.rb" | head -10
+# ~/.prompts/document.md
+/config model = gpt-4o-mini
+/shell find [PROJECT_DIR] -name "*.rb" | head -10
 
 Generate documentation for the Ruby project shown above.
 Include: API references, usage examples, and setup instructions.
@@ -1253,7 +1253,7 @@ Include: API references, usage examples, and setup instructions.
 
 #### Multi-Model Decision Making
 ```bash
-# ~/.prompts/decision_maker.txt
+# ~/.prompts/decision_maker.md
 # Compare different AI perspectives on complex decisions
 
 What are the pros and cons of [DECISION_TOPIC]?
@@ -1289,7 +1289,7 @@ Create executable prompts:
 
 Summarize the tropical storm outlook fpr the Atlantic, Caribbean Sea and Gulf of America.
 
-//webpage https://www.nhc.noaa.gov/text/refresh/MIATWOAT+shtml/201724_MIATWOAT.shtml
+/webpage https://www.nhc.noaa.gov/text/refresh/MIATWOAT+shtml/201724_MIATWOAT.shtml
 ```
 
 Usage:
@@ -1302,7 +1302,7 @@ Usage:
 
 #### The run Prompt
 ```bash
-# ~/.prompts/run.txt
+# ~/.prompts/run.md
 # Desc: A configuration only prompt file for use with executable prompts
 #       Put whatever you want here to setup the configuration desired.
 #       You could also add a system prompt to preface your intended prompt
@@ -1312,7 +1312,7 @@ Usage: `echo "What is the meaning of life?" | aia run`
 
 #### The Ad Hoc One-shot Prompt
 ```bash
-# ~/.prompts/ad_hoc.txt
+# ~/.prompts/ad_hoc.md
 [WHAT_NOW_HUMAN]
 ```
 Usage: `aia ad_hoc` - perfect for any quick one-shot question without cluttering shell history.
@@ -1358,16 +1358,16 @@ AIA executes shell commands and Ruby code embedded in prompts. This provides pow
 
 ```bash
 # ✅ Good: Use parameters for sensitive data
-//config api_key = [API_KEY]
+/config api_key = [API_KEY]
 
 # ❌ Bad: Hardcode secrets
-//config api_key = sk-1234567890abcdef
+/config api_key = sk-1234567890abcdef
 
 # ✅ Good: Validate shell commands
-//shell ls -la /safe/directory
+/shell ls -la /safe/directory
 
 # ❌ Bad: Dangerous shell commands
-//shell rm -rf / # Never do this!
+/shell rm -rf / # Never do this!
 ```
 
 ### Recommended Security Setup
@@ -1375,7 +1375,7 @@ AIA executes shell commands and Ruby code embedded in prompts. This provides pow
 ```bash
 # Set restrictive permissions on prompts directory
 chmod 700 ~/.prompts
-chmod 600 ~/.prompts/*.txt
+chmod 600 ~/.prompts/*.md
 ```
 
 ## Troubleshooting
@@ -1388,7 +1388,7 @@ chmod 600 ~/.prompts/*.txt
 ls $AIA_PROMPTS__DIR
 
 # Verify prompt file exists
-ls ~/.prompts/my_prompt.txt
+ls ~/.prompts/my_prompt.md
 
 # Use fuzzy search
 aia --fuzzy
@@ -1478,7 +1478,7 @@ aia --fatal --chat
 
 **Large prompt processing:**
 - Break into smaller prompts using `--pipeline`
-- Use `//include` selectively instead of large files
+- Use `/include` selectively instead of large files
 - Consider model context limits
 
 ## Development

data/Rakefile

@@ -25,14 +25,19 @@ Minitest::TestTask.create(:test) do |t|
   t.libs        << "test"
   t.libs        << "lib"
   t.warning     = false
+  # Load SimpleCov before minitest/autorun so at_exit ordering is correct
+  t.test_prelude = 'ENV["TEST_SUITE"]="unit"; require "simplecov_helper"'
   # Include all unit tests under test/, excluding integration tests
-  t.test_globs  = ["test/**/*_test.rb", "!test/integration/**/*_test.rb"]
+  # Dir.glob does not support ! negation, so compute the file list manually
+  t.test_globs  = Dir["test/**/*_test.rb"].reject { |f| f.start_with?("test/integration/") }
 end
 
 Minitest::TestTask.create(:integration) do |t|
   t.libs        << "test"
   t.libs        << "lib"
   t.warning     = false
+  # Load SimpleCov before minitest/autorun so at_exit ordering is correct
+  t.test_prelude = 'ENV["TEST_SUITE"]="integration"; require "simplecov_helper"'
   t.test_globs  = ["test/integration/**/*_test.rb"]
 end