aia 2.0.0.0.pre.alpha → 2.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.version +1 -1
- data/CHANGELOG.md +151 -228
- data/README.md +42 -19
- data/bin/aia +8 -3
- data/lib/aia/aia_completion.bash +2 -3
- data/lib/aia/aia_completion.fish +6 -5
- data/lib/aia/aia_completion.zsh +2 -3
- data/lib/aia/chat_loop.rb +24 -66
- data/lib/aia/config/cli_parser.rb +164 -123
- data/lib/aia/config/defaults.yml +12 -39
- data/lib/aia/config/mcp_parser.rb +42 -40
- data/lib/aia/config/model_spec.rb +8 -14
- data/lib/aia/config/validator.rb +144 -156
- data/lib/aia/config/value_caster.rb +76 -0
- data/lib/aia/config.rb +72 -54
- data/lib/aia/content_extractor.rb +2 -0
- data/lib/aia/cost_calculator.rb +1 -0
- data/lib/aia/crew.rb +29 -19
- data/lib/aia/debate_handler.rb +45 -20
- data/lib/aia/delegate_handler.rb +7 -3
- data/lib/aia/directive.rb +10 -8
- data/lib/aia/directives/configuration_directives.rb +164 -109
- data/lib/aia/directives/context_directives.rb +55 -40
- data/lib/aia/directives/execution_directives.rb +25 -25
- data/lib/aia/directives/model_directives.rb +112 -195
- data/lib/aia/directives/trakflow_directives.rb +27 -9
- data/lib/aia/directives/utility_directives.rb +86 -87
- data/lib/aia/directives/web_and_file_directives.rb +83 -63
- data/lib/aia/fact_asserter.rb +3 -3
- data/lib/aia/history_transfer.rb +64 -24
- data/lib/aia/layered_orchestrator.rb +66 -43
- data/lib/aia/logger.rb +27 -62
- data/lib/aia/mcp_config_normalizer.rb +27 -14
- data/lib/aia/mcp_connection_manager.rb +193 -186
- data/lib/aia/mcp_discovery.rb +43 -15
- data/lib/aia/mcp_grouper.rb +2 -1
- data/lib/aia/mcp_server_config.rb +48 -0
- data/lib/aia/mcp_utility.rb +28 -20
- data/lib/aia/mention_router.rb +22 -52
- data/lib/aia/modality_query.rb +36 -0
- data/lib/aia/model_alias_registry.rb +11 -11
- data/lib/aia/model_registry.rb +75 -0
- data/lib/aia/network_builder.rb +17 -11
- data/lib/aia/network_memory_manager.rb +6 -6
- data/lib/aia/patches/ruby_llm_streaming_error.rb +21 -4
- data/lib/aia/patches/ruby_llm_tool_param_compat.rb +18 -0
- data/lib/aia/pipeline_orchestrator.rb +88 -45
- data/lib/aia/plugin_monitor.rb +9 -6
- data/lib/aia/prompt_decomposer.rb +6 -4
- data/lib/aia/prompt_handler.rb +90 -69
- data/lib/aia/provider_registry.rb +105 -0
- data/lib/aia/robot_builder.rb +1 -1
- data/lib/aia/robot_factory.rb +77 -69
- data/lib/aia/robot_namer.rb +2 -8
- data/lib/aia/robot_sync.rb +79 -0
- data/lib/aia/role_catalog.rb +89 -0
- data/lib/aia/session.rb +32 -14
- data/lib/aia/session_tracker.rb +39 -41
- data/lib/aia/similarity_scorer.rb +5 -3
- data/lib/aia/skill_utils.rb +60 -19
- data/lib/aia/spawn_handler.rb +16 -4
- data/lib/aia/spawn_spec_parser.rb +6 -7
- data/lib/aia/special_mode_handler.rb +80 -57
- data/lib/aia/speech.rb +103 -0
- data/lib/aia/startup_coordinator.rb +17 -91
- data/lib/aia/streaming_runner.rb +16 -5
- data/lib/aia/system_prompt_assembler.rb +20 -15
- data/lib/aia/task_board.rb +60 -0
- data/lib/aia/task_coordinator.rb +10 -5
- data/lib/aia/timing.rb +15 -0
- data/lib/aia/tool_approver.rb +205 -0
- data/lib/aia/tool_filter.rb +1 -9
- data/lib/aia/tool_filter_strategy.rb +39 -25
- data/lib/aia/tool_introspection.rb +25 -0
- data/lib/aia/tool_loader.rb +71 -31
- data/lib/aia/tool_utility.rb +6 -5
- data/lib/aia/tools/delegate_to_foreman_tool.rb +6 -4
- data/lib/aia/tools/recruit_robot_tool.rb +12 -12
- data/lib/aia/tools/reskill_robot_tool.rb +7 -7
- data/lib/aia/tools/task_board_tool.rb +17 -16
- data/lib/aia/trakflow_bridge.rb +19 -11
- data/lib/aia/turn_state.rb +32 -8
- data/lib/aia/ui_presenter.rb +83 -59
- data/lib/aia/utility.rb +8 -24
- data/lib/aia/variable_input_collector.rb +1 -3
- data/lib/aia/verification_network.rb +10 -12
- data/lib/aia.rb +49 -8
- metadata +27 -162
- data/.better-commits.json +0 -150
- data/.config/tocer/configuration.yml +0 -6
- data/.envrc +0 -15
- data/.loki +0 -231
- data/.quality/flay_baseline.txt +0 -1
- data/.quality/flog_baseline.txt +0 -29
- data/.quality/reek_baseline.txt +0 -80
- data/.rubocop.yml +0 -116
- data/COMMITS.md +0 -196
- data/IMPLEMENTATION_PLAN.md +0 -506
- data/Rakefile +0 -160
- data/architecture_review.md +0 -314
- data/docs/AGENTS.md +0 -40
- data/docs/advanced-prompting.md +0 -814
- data/docs/assets/images/aia.png +0 -0
- data/docs/cli-reference.md +0 -1241
- data/docs/configuration.md +0 -747
- data/docs/contributing.md +0 -386
- data/docs/directives-reference.md +0 -1145
- data/docs/examples/index.md +0 -277
- data/docs/examples/mcp/index.md +0 -475
- data/docs/examples/prompts/analysis/index.md +0 -78
- data/docs/examples/prompts/automation/index.md +0 -109
- data/docs/examples/prompts/development/index.md +0 -125
- data/docs/examples/prompts/index.md +0 -333
- data/docs/examples/prompts/learning/index.md +0 -127
- data/docs/examples/prompts/writing/index.md +0 -62
- data/docs/examples/tools/index.md +0 -282
- data/docs/faq.md +0 -578
- data/docs/guides/available-models.md +0 -366
- data/docs/guides/basic-usage.md +0 -478
- data/docs/guides/chat.md +0 -680
- data/docs/guides/crew.md +0 -239
- data/docs/guides/executable-prompts.md +0 -331
- data/docs/guides/first-prompt.md +0 -454
- data/docs/guides/getting-started.md +0 -455
- data/docs/guides/image-generation.md +0 -507
- data/docs/guides/index.md +0 -48
- data/docs/guides/local-models.md +0 -306
- data/docs/guides/migrate-prompts.md +0 -335
- data/docs/guides/models.md +0 -1017
- data/docs/guides/shared-tools.md +0 -254
- data/docs/guides/tools.md +0 -831
- data/docs/index.md +0 -259
- data/docs/installation.md +0 -274
- data/docs/mcp-integration.md +0 -603
- data/docs/prompt_management.md +0 -665
- data/docs/security.md +0 -674
- data/docs/special_projects_guide.md +0 -386
- data/docs/tools-and-mcp-examples.md +0 -1211
- data/docs/workflows-and-pipelines.md +0 -636
- data/examples/.gitignore +0 -2
- data/examples/00_setup_aia.sh +0 -111
- data/examples/01_basic_usage.sh +0 -23
- data/examples/02_frontmatter.sh +0 -33
- data/examples/03_shell_integration.sh +0 -55
- data/examples/04_erb_templating.sh +0 -56
- data/examples/05_shell_then_erb.sh +0 -38
- data/examples/06_prompt_chaining.sh +0 -59
- data/examples/07_pipeline.sh +0 -46
- data/examples/08_context_files.sh +0 -43
- data/examples/09_roles.sh +0 -67
- data/examples/10_stdin_piping.sh +0 -49
- data/examples/11_multi_model.sh +0 -65
- data/examples/12_token_usage.sh +0 -52
- data/examples/13_cost_tracking.sh +0 -68
- data/examples/14_output_file.sh +0 -91
- data/examples/15_parameters.sh +0 -68
- data/examples/16_directives.sh +0 -113
- data/examples/17_require_and_conditionals.sh +0 -68
- data/examples/18_tools.sh +0 -61
- data/examples/19_local_tools.sh +0 -34
- data/examples/20_mcp_servers.sh +0 -102
- data/examples/21_executable_prompts.sh +0 -78
- data/examples/22_chat_mode.sh +0 -217
- data/examples/23_verify.sh +0 -139
- data/examples/24_decompose.sh +0 -139
- data/examples/25_spawn.sh +0 -139
- data/examples/26_debate.sh +0 -97
- data/examples/27_mention_routing.sh +0 -157
- data/examples/28_model_switching.sh +0 -106
- data/examples/29_agent_harness.sh +0 -177
- data/examples/README.md +0 -321
- data/examples/advanced_multi_robot_capabilities_without_examples.md +0 -106
- data/examples/aia_config.yml +0 -22
- data/examples/aia_config_orchestrator.yml +0 -45
- data/examples/aia_config_with_mcp.yml +0 -21
- data/examples/common.sh +0 -39
- data/examples/context/project_goals.md +0 -6
- data/examples/context/tech_stack.md +0 -7
- data/examples/directives/timestamp_directive.rb +0 -22
- data/examples/mcp/filesystem.json +0 -9
- data/examples/prompts_dir/analyze.md +0 -2
- data/examples/prompts_dir/brainstorm.md +0 -2
- data/examples/prompts_dir/conditional.md +0 -17
- data/examples/prompts_dir/creative.md +0 -4
- data/examples/prompts_dir/erbinfo.md +0 -5
- data/examples/prompts_dir/erbinfo_raw.md +0 -8
- data/examples/prompts_dir/evaluate.md +0 -2
- data/examples/prompts_dir/explain_joke.md +0 -1
- data/examples/prompts_dir/explain_recursion.md +0 -1
- data/examples/prompts_dir/fun_fact +0 -3
- data/examples/prompts_dir/greeting.md +0 -8
- data/examples/prompts_dir/greeting_required.md +0 -7
- data/examples/prompts_dir/hello.md +0 -1
- data/examples/prompts_dir/includes/ruby_facts.md +0 -4
- data/examples/prompts_dir/limerick.md +0 -1
- data/examples/prompts_dir/list_with_mcp.md +0 -3
- data/examples/prompts_dir/pick_best.md +0 -2
- data/examples/prompts_dir/project_summary +0 -12
- data/examples/prompts_dir/quiz_with_include.md +0 -6
- data/examples/prompts_dir/require_demo.md +0 -5
- data/examples/prompts_dir/roles/formal.md +0 -3
- data/examples/prompts_dir/roles/orchestrator.md +0 -21
- data/examples/prompts_dir/roles/pirate.md +0 -3
- data/examples/prompts_dir/shell_then_erb.md +0 -6
- data/examples/prompts_dir/sort_compare.md +0 -2
- data/examples/prompts_dir/summarize_context.md +0 -2
- data/examples/prompts_dir/sysinfo.md +0 -5
- data/examples/prompts_dir/sysinfo_raw.md +0 -8
- data/examples/prompts_dir/tagline.md +0 -1
- data/examples/prompts_dir/tell_joke.md +0 -1
- data/examples/prompts_dir/tell_joke_with_next.md +0 -4
- data/examples/prompts_dir/use_local_tool.md +0 -8
- data/examples/prompts_dir/use_tools.md +0 -8
- data/examples/prompts_dir/weather.md +0 -2
- data/examples/prompts_dir/whats_new.md +0 -2
- data/examples/prompts_dir/with_timestamp.md +0 -5
- data/examples/requirements/sinatra_taskflow_app.md +0 -139
- data/examples/rules/01_classify_ruby.rb +0 -16
- data/examples/rules/02_prefer_claude_for_code.rb +0 -19
- data/examples/rules/03_gate_prompt_length.rb +0 -19
- data/examples/rules/04_tool_selection.rb +0 -41
- data/examples/rules/README.md +0 -30
- data/examples/run_all.sh +0 -294
- data/examples/tools/word_count_tool.rb +0 -30
- data/lib/AGENTS.md +0 -57
- data/lib/aia/model_switch_handler.rb +0 -100
- data/mcp_servers/README.md +0 -110
- data/mcp_servers/apple-mcp.json +0 -8
- data/mcp_servers/filesystem.json +0 -9
- data/mcp_servers/mcp_server_chart.json +0 -11
- data/mcp_servers/playwright_one.json +0 -8
- data/mcp_servers/playwright_server_definition.json +0 -9
- data/mcp_servers/playwright_two.json +0 -8
- data/mcp_servers/tavily_mcp_server.json +0 -8
- data/mkdocs.yml +0 -169
data/docs/guides/chat.md
DELETED
|
@@ -1,680 +0,0 @@
|
|
|
1
|
-
# Chat Mode Guide
|
|
2
|
-
|
|
3
|
-
AIA's chat mode provides interactive conversations with AI models, maintaining context and supporting advanced features like multi-model interactions, tool usage, and persistent sessions.
|
|
4
|
-
|
|
5
|
-
## Starting a Chat Session
|
|
6
|
-
|
|
7
|
-
### Basic Chat
|
|
8
|
-
```bash
|
|
9
|
-
# Start an interactive chat session
|
|
10
|
-
aia --chat
|
|
11
|
-
|
|
12
|
-
# Start chat with a specific model
|
|
13
|
-
aia --chat --model gpt-4
|
|
14
|
-
|
|
15
|
-
# Start chat with initial context
|
|
16
|
-
aia --chat --role assistant my_context.txt
|
|
17
|
-
```
|
|
18
|
-
|
|
19
|
-
### Chat with Initial Prompts
|
|
20
|
-
```bash
|
|
21
|
-
# Begin chat after processing a prompt
|
|
22
|
-
aia --chat my_initial_prompt
|
|
23
|
-
|
|
24
|
-
# Chat with system prompt
|
|
25
|
-
aia --chat --system-prompt helpful_assistant
|
|
26
|
-
|
|
27
|
-
# Chat with role-based context
|
|
28
|
-
aia --chat --role code_expert debugging_session
|
|
29
|
-
```
|
|
30
|
-
|
|
31
|
-
## Chat Interface
|
|
32
|
-
|
|
33
|
-
### Basic Commands
|
|
34
|
-
Once in chat mode, you can use these commands:
|
|
35
|
-
|
|
36
|
-
- **Regular messages**: Type normally and press Enter
|
|
37
|
-
- **`/help`**: Show available chat commands
|
|
38
|
-
- **`/exit`** or **`/quit`**: End the chat session
|
|
39
|
-
- **`/clear`**: Clear conversation history
|
|
40
|
-
- **`/save filename.md`**: Save conversation to file
|
|
41
|
-
- **`/model model_name`**: Switch AI model
|
|
42
|
-
- **`/temperature 0.8`**: Adjust creativity level
|
|
43
|
-
- **`/tools`**: List available tools
|
|
44
|
-
- **`/context`**: Show current context
|
|
45
|
-
- **`/robots`**: List active robots and their `@mention` handles
|
|
46
|
-
|
|
47
|
-
### Special Features
|
|
48
|
-
|
|
49
|
-
#### Multi-line Input
|
|
50
|
-
```
|
|
51
|
-
You: ```
|
|
52
|
-
This is a multi-line input.
|
|
53
|
-
You can write code, long explanations,
|
|
54
|
-
or complex queries across multiple lines.
|
|
55
|
-
```
|
|
56
|
-
|
|
57
|
-
#### File Upload During Chat
|
|
58
|
-
```
|
|
59
|
-
You: Please analyze this file:
|
|
60
|
-
/include my_data.csv
|
|
61
|
-
|
|
62
|
-
What patterns do you see?
|
|
63
|
-
```
|
|
64
|
-
|
|
65
|
-
#### Code Execution
|
|
66
|
-
```
|
|
67
|
-
The current date and time is:
|
|
68
|
-
/ruby Time.now
|
|
69
|
-
|
|
70
|
-
Files in the current directory are:
|
|
71
|
-
/shell ls -la
|
|
72
|
-
|
|
73
|
-
which files are over 1 week old?
|
|
74
|
-
```
|
|
75
|
-
|
|
76
|
-
> **Security Warning**: The `/ruby` and `/shell` directives execute code directly on your machine with your user permissions. `/ruby` runs arbitrary Ruby via `eval()` and `/shell` invokes system commands. Only use these directives with trusted prompts. Never run prompts from untrusted sources that contain these directives without reviewing them first.
|
|
77
|
-
|
|
78
|
-
## Advanced Chat Features
|
|
79
|
-
|
|
80
|
-
### Multi-Model Conversations
|
|
81
|
-
|
|
82
|
-
#### @mention Routing
|
|
83
|
-
In a multi-model network, direct your message to a specific robot by prefixing its name with `@` (e.g., `@tobor What do you think?`). Use `/robots` to see active robot names and their `@mention` handles.
|
|
84
|
-
|
|
85
|
-
#### Consensus Mode
|
|
86
|
-
```bash
|
|
87
|
-
# Start chat with multiple models seeking consensus
|
|
88
|
-
aia --chat --model "gpt-4,claude-3-sonnet,gemini-pro" --consensus
|
|
89
|
-
|
|
90
|
-
# Models will collaborate to provide unified responses
|
|
91
|
-
```
|
|
92
|
-
|
|
93
|
-
#### Parallel Responses
|
|
94
|
-
```bash
|
|
95
|
-
# Get responses from multiple models simultaneously
|
|
96
|
-
aia --chat --model "gpt-4,claude-3-sonnet" --no-consensus
|
|
97
|
-
|
|
98
|
-
# You'll see separate responses from each model
|
|
99
|
-
```
|
|
100
|
-
|
|
101
|
-
#### Model Comparison
|
|
102
|
-
```
|
|
103
|
-
You: Compare these approaches to solving the problem:
|
|
104
|
-
/compare "Explain recursion vs iteration" --models gpt-4,claude-3-sonnet
|
|
105
|
-
|
|
106
|
-
Which explanation is clearer?
|
|
107
|
-
```
|
|
108
|
-
|
|
109
|
-
### Context Management
|
|
110
|
-
|
|
111
|
-
#### Persistent Context
|
|
112
|
-
AIA maintains conversation context automatically:
|
|
113
|
-
```
|
|
114
|
-
You: I'm working on a Python web application using Flask.
|
|
115
|
-
AI: Great! Flask is an excellent choice for web development...
|
|
116
|
-
|
|
117
|
-
You: How do I handle user authentication?
|
|
118
|
-
AI: For your Flask application, here are several authentication options...
|
|
119
|
-
```
|
|
120
|
-
|
|
121
|
-
#### Context Checkpoints
|
|
122
|
-
Create savepoints in your conversation to easily return to specific moments:
|
|
123
|
-
|
|
124
|
-
```
|
|
125
|
-
You: Let's explore different authentication approaches for Flask.
|
|
126
|
-
AI: I can help you explore various authentication methods...
|
|
127
|
-
|
|
128
|
-
You: /checkpoint auth_start
|
|
129
|
-
|
|
130
|
-
You: Tell me about JWT authentication.
|
|
131
|
-
AI: JWT (JSON Web Tokens) authentication is a stateless approach...
|
|
132
|
-
|
|
133
|
-
You: /checkpoint jwt_discussion
|
|
134
|
-
|
|
135
|
-
You: What about OAuth integration?
|
|
136
|
-
AI: OAuth provides a robust framework for authentication...
|
|
137
|
-
|
|
138
|
-
You: Actually, let's go back to the JWT discussion
|
|
139
|
-
You: /restore jwt_discussion
|
|
140
|
-
|
|
141
|
-
You: /context
|
|
142
|
-
=== Chat Context ===
|
|
143
|
-
Total messages: 6
|
|
144
|
-
Checkpoints: auth_start, jwt_discussion
|
|
145
|
-
|
|
146
|
-
1. [System]: You are a helpful assistant
|
|
147
|
-
2. [User]: Let's explore different authentication approaches for Flask.
|
|
148
|
-
3. [Assistant]: I can help you explore various authentication methods...
|
|
149
|
-
|
|
150
|
-
📍 [Checkpoint: auth_start]
|
|
151
|
-
----------------------------------------
|
|
152
|
-
4. [User]: Tell me about JWT authentication.
|
|
153
|
-
5. [Assistant]: JWT (JSON Web Tokens) authentication is a stateless approach...
|
|
154
|
-
|
|
155
|
-
📍 [Checkpoint: jwt_discussion]
|
|
156
|
-
----------------------------------------
|
|
157
|
-
=== End of Context ===
|
|
158
|
-
```
|
|
159
|
-
|
|
160
|
-
**Checkpoint Commands**:
|
|
161
|
-
- `/checkpoint` - Create auto-numbered checkpoint (1, 2, 3...)
|
|
162
|
-
- `/checkpoint name` - Create named checkpoint
|
|
163
|
-
- `/restore` - Restore to last checkpoint
|
|
164
|
-
- `/restore name` - Restore to specific checkpoint
|
|
165
|
-
- `/cp name` - Short alias for checkpoint
|
|
166
|
-
|
|
167
|
-
**Use Cases for Checkpoints**:
|
|
168
|
-
- **Exploring alternatives**: Save before trying different approaches
|
|
169
|
-
- **Debugging conversations**: Return to working state after errors
|
|
170
|
-
- **Session branching**: Explore multiple conversation paths
|
|
171
|
-
- **Learning sessions**: Bookmark important explanations
|
|
172
|
-
|
|
173
|
-
#### Context Inspection
|
|
174
|
-
```
|
|
175
|
-
You: /context
|
|
176
|
-
# Shows current conversation history with checkpoint markers
|
|
177
|
-
|
|
178
|
-
You: /review
|
|
179
|
-
# Alternative command for context inspection
|
|
180
|
-
```
|
|
181
|
-
|
|
182
|
-
#### Context Clearing
|
|
183
|
-
```
|
|
184
|
-
You: /clear
|
|
185
|
-
# Clears conversation history and all checkpoints while keeping session active
|
|
186
|
-
```
|
|
187
|
-
|
|
188
|
-
### Tool Integration in Chat
|
|
189
|
-
|
|
190
|
-
#### Enabling Tools
|
|
191
|
-
```bash
|
|
192
|
-
# Start chat with specific tools
|
|
193
|
-
aia --chat --tools ./my_tools.rb
|
|
194
|
-
|
|
195
|
-
# Start with tool directory
|
|
196
|
-
aia --chat --tools ./tools/
|
|
197
|
-
|
|
198
|
-
# Restrict tool access
|
|
199
|
-
aia --chat --tools ./tools/ --allowed-tools "file_reader,calculator"
|
|
200
|
-
```
|
|
201
|
-
|
|
202
|
-
#### Using Tools in Conversation
|
|
203
|
-
```
|
|
204
|
-
You: Can you analyze the performance metrics in this log file?
|
|
205
|
-
/tools performance_analyzer
|
|
206
|
-
/include /var/log/app.log
|
|
207
|
-
|
|
208
|
-
AI: I'll analyze the performance data using the performance analyzer tool...
|
|
209
|
-
```
|
|
210
|
-
|
|
211
|
-
#### Tool Discovery
|
|
212
|
-
```
|
|
213
|
-
You: /tools
|
|
214
|
-
Available Tools:
|
|
215
|
-
- file_analyzer: Analyze file contents and structure
|
|
216
|
-
- web_scraper: Extract data from web pages
|
|
217
|
-
- calculator: Perform complex mathematical calculations
|
|
218
|
-
```
|
|
219
|
-
|
|
220
|
-
## Chat Session Types
|
|
221
|
-
|
|
222
|
-
### Code Review Session
|
|
223
|
-
```bash
|
|
224
|
-
# Start specialized code review chat
|
|
225
|
-
aia --chat --role code_expert --system-prompt code_reviewer
|
|
226
|
-
|
|
227
|
-
You: I need help reviewing this Python function:
|
|
228
|
-
/include my_function.py
|
|
229
|
-
|
|
230
|
-
AI: I'll review this code for bugs, performance issues, and best practices...
|
|
231
|
-
|
|
232
|
-
You: What about security concerns?
|
|
233
|
-
AI: Looking at the security aspects of your function...
|
|
234
|
-
|
|
235
|
-
You: Can you suggest unit tests for this?
|
|
236
|
-
AI: Here are comprehensive unit tests for your function...
|
|
237
|
-
```
|
|
238
|
-
|
|
239
|
-
### Data Analysis Session
|
|
240
|
-
```bash
|
|
241
|
-
# Start data analysis chat with tools
|
|
242
|
-
aia --chat --tools ./analysis_tools/ --model claude-3-sonnet
|
|
243
|
-
|
|
244
|
-
You: I have a dataset I need to analyze:
|
|
245
|
-
/include data.csv
|
|
246
|
-
|
|
247
|
-
AI: I can help you analyze this dataset. Let me start by examining its structure...
|
|
248
|
-
|
|
249
|
-
You: Focus on the correlation between sales and marketing spend
|
|
250
|
-
AI: I'll analyze the correlation using statistical tools...
|
|
251
|
-
```
|
|
252
|
-
|
|
253
|
-
### Writing Session
|
|
254
|
-
```bash
|
|
255
|
-
# Start creative writing session
|
|
256
|
-
aia --chat --model gpt-4 --temperature 1.2 --role creative_writer
|
|
257
|
-
|
|
258
|
-
You: Help me write a technical blog post about microservices
|
|
259
|
-
AI: I'd be happy to help! Let's start by outlining the key points...
|
|
260
|
-
|
|
261
|
-
You: Make it more engaging for developers
|
|
262
|
-
AI: Here's how we can make it more engaging...
|
|
263
|
-
```
|
|
264
|
-
|
|
265
|
-
### Learning Session
|
|
266
|
-
```bash
|
|
267
|
-
# Start educational chat
|
|
268
|
-
aia --chat --role teacher --system-prompt patient_explainer
|
|
269
|
-
|
|
270
|
-
You: Explain how blockchain works, but I'm completely new to this
|
|
271
|
-
AI: Let me explain blockchain in simple terms, starting from the basics...
|
|
272
|
-
|
|
273
|
-
You: Can you give me a practical example?
|
|
274
|
-
AI: Absolutely! Let's use a simple example everyone can relate to...
|
|
275
|
-
```
|
|
276
|
-
|
|
277
|
-
## Voice and Audio Features
|
|
278
|
-
|
|
279
|
-
### Text-to-Speech
|
|
280
|
-
|
|
281
|
-
`--speak` runs a three-stage pipeline after each AI response:
|
|
282
|
-
|
|
283
|
-
1. **Generation** — LLM streams text to the terminal (`Processing...`)
|
|
284
|
-
2. **Conversion** — text is converted to an audio file (`Converting to audio...`)
|
|
285
|
-
3. **Playback** — audio file is played (`Speaking...`)
|
|
286
|
-
|
|
287
|
-
**Local TTS (default):** the macOS `say` command handles both conversion and
|
|
288
|
-
playback in one step, so it shows a single `Speaking...` spinner.
|
|
289
|
-
|
|
290
|
-
```bash
|
|
291
|
-
# Enable speech (uses macOS say, system default voice)
|
|
292
|
-
aia --chat --speak
|
|
293
|
-
|
|
294
|
-
# Choose a specific macOS voice (run `say -v '?'` to list available voices)
|
|
295
|
-
aia --chat --speak --voice Samantha
|
|
296
|
-
aia --chat --speak --voice Alex
|
|
297
|
-
```
|
|
298
|
-
|
|
299
|
-
**OpenAI TTS:** point `speak_command` at `~/.config/aia/tts.sh` (installed with
|
|
300
|
-
AIA). The script converts text to an audio file; AIA plays it with `afplay` and
|
|
301
|
-
shows separate spinners for each stage.
|
|
302
|
-
|
|
303
|
-
```bash
|
|
304
|
-
aia --chat --speak \
|
|
305
|
-
--speak-command ~/.config/aia/tts.sh \
|
|
306
|
-
--speech-model tts-1-hd \
|
|
307
|
-
--voice nova \
|
|
308
|
-
my_prompt
|
|
309
|
-
```
|
|
310
|
-
|
|
311
|
-
```yaml
|
|
312
|
-
# ~/.config/aia/aia.yml
|
|
313
|
-
audio:
|
|
314
|
-
speak_command: ~/.config/aia/tts.sh
|
|
315
|
-
speech_model: tts-1-hd # passed as SPEECH_MODEL env var to the script
|
|
316
|
-
voice: nova # passed as AIA_AUDIO__VOICE env var
|
|
317
|
-
```
|
|
318
|
-
|
|
319
|
-
### Audio Input
|
|
320
|
-
```bash
|
|
321
|
-
# Use speech-to-text for input
|
|
322
|
-
aia --chat --transcription-model whisper-1 audio_input.wav
|
|
323
|
-
```
|
|
324
|
-
|
|
325
|
-
## Session Management
|
|
326
|
-
|
|
327
|
-
### Saving Conversations
|
|
328
|
-
```
|
|
329
|
-
# Within chat
|
|
330
|
-
You: /save project_discussion.md
|
|
331
|
-
Conversation saved to project_discussion.md
|
|
332
|
-
|
|
333
|
-
# Or with full path
|
|
334
|
-
You: /save /path/to/conversations/analysis_session.md
|
|
335
|
-
```
|
|
336
|
-
|
|
337
|
-
### Loading Previous Context
|
|
338
|
-
```bash
|
|
339
|
-
# Start chat with previous conversation
|
|
340
|
-
aia --chat --include previous_session.md
|
|
341
|
-
|
|
342
|
-
# This loads the conversation as context
|
|
343
|
-
```
|
|
344
|
-
|
|
345
|
-
### Switching Models and Providers Mid-Session
|
|
346
|
-
|
|
347
|
-
One of AIA's most practical features is the ability to change models — and even providers — on the fly during a chat session. There is no need to restart; the switch takes effect immediately.
|
|
348
|
-
|
|
349
|
-
#### Switch to a Different Model
|
|
350
|
-
|
|
351
|
-
```
|
|
352
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
353
|
-
/model gpt-4o-mini
|
|
354
|
-
|
|
355
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
356
|
-
/model
|
|
357
|
-
Current Model:
|
|
358
|
-
==============
|
|
359
|
-
{id: "gpt-4o-mini",
|
|
360
|
-
name: "GPT-4o mini",
|
|
361
|
-
provider: "openai",
|
|
362
|
-
...}
|
|
363
|
-
```
|
|
364
|
-
|
|
365
|
-
#### Switch Providers
|
|
366
|
-
|
|
367
|
-
The `/model` directive works across providers. Move from Anthropic to OpenAI to Google (or any supported provider) without leaving your session:
|
|
368
|
-
|
|
369
|
-
```
|
|
370
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
371
|
-
/model claude-sonnet-4
|
|
372
|
-
# Now using Anthropic
|
|
373
|
-
|
|
374
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
375
|
-
/model gpt-4o
|
|
376
|
-
# Now using OpenAI
|
|
377
|
-
|
|
378
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
379
|
-
/model gemini-2.0-flash
|
|
380
|
-
# Now using Google
|
|
381
|
-
```
|
|
382
|
-
|
|
383
|
-
#### Go from Single Model to Multi-Model
|
|
384
|
-
|
|
385
|
-
You can switch from a single model to a multi-model configuration by providing a comma-separated list. Each model gets its own conversation context and responds independently:
|
|
386
|
-
|
|
387
|
-
```
|
|
388
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
389
|
-
/model gpt-4o-mini, claude-sonnet-4
|
|
390
|
-
|
|
391
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
392
|
-
/model
|
|
393
|
-
Multi-Model Configuration:
|
|
394
|
-
==========================
|
|
395
|
-
Model count: 2
|
|
396
|
-
Primary model: gpt-4o-mini (used for consensus when --consensus flag is enabled)
|
|
397
|
-
...
|
|
398
|
-
```
|
|
399
|
-
|
|
400
|
-
You can also assign roles inline using the `model=role` syntax:
|
|
401
|
-
|
|
402
|
-
```
|
|
403
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
404
|
-
/model gpt-4o=architect, claude-sonnet-4=security
|
|
405
|
-
```
|
|
406
|
-
|
|
407
|
-
#### Go from Multi-Model Back to Single
|
|
408
|
-
|
|
409
|
-
Specify just one model name to return to single-model mode:
|
|
410
|
-
|
|
411
|
-
```
|
|
412
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
413
|
-
/model claude-sonnet-4
|
|
414
|
-
```
|
|
415
|
-
|
|
416
|
-
#### View Current Model
|
|
417
|
-
|
|
418
|
-
Use `/model` with no arguments to inspect the active model configuration:
|
|
419
|
-
|
|
420
|
-
```
|
|
421
|
-
Follow up (cntl-D or 'exit' to end) #=>
|
|
422
|
-
/model
|
|
423
|
-
```
|
|
424
|
-
|
|
425
|
-
This shows the model ID, provider, context window, pricing, capabilities, and more.
|
|
426
|
-
|
|
427
|
-
#### Adjust Generation Parameters
|
|
428
|
-
|
|
429
|
-
Fine-tune how the active model responds:
|
|
430
|
-
|
|
431
|
-
```
|
|
432
|
-
# Adjust creativity
|
|
433
|
-
You: /temperature 0.3
|
|
434
|
-
|
|
435
|
-
# Adjust nucleus sampling
|
|
436
|
-
You: /top_p 0.9
|
|
437
|
-
```
|
|
438
|
-
|
|
439
|
-
## Chat Workflows
|
|
440
|
-
|
|
441
|
-
### Research and Analysis Workflow
|
|
442
|
-
1. **Information Gathering**: Load documents and data
|
|
443
|
-
2. **Initial Analysis**: Ask broad questions
|
|
444
|
-
3. **Deep Dive**: Focus on specific areas
|
|
445
|
-
4. **Synthesis**: Combine insights
|
|
446
|
-
5. **Documentation**: Save findings
|
|
447
|
-
|
|
448
|
-
```
|
|
449
|
-
You: I'm researching market trends in AI development
|
|
450
|
-
/include market_report.pdf
|
|
451
|
-
/include competitor_analysis.csv
|
|
452
|
-
|
|
453
|
-
AI: I'll help you analyze these market trends...
|
|
454
|
-
|
|
455
|
-
You: What are the key growth drivers?
|
|
456
|
-
AI: Based on the data, here are the main growth drivers...
|
|
457
|
-
|
|
458
|
-
You: How do our competitors compare?
|
|
459
|
-
AI: Looking at the competitive landscape...
|
|
460
|
-
|
|
461
|
-
You: /save ai_market_research.md
|
|
462
|
-
```
|
|
463
|
-
|
|
464
|
-
### Development Workflow
|
|
465
|
-
1. **Code Review**: Analyze existing code
|
|
466
|
-
2. **Problem Solving**: Debug issues
|
|
467
|
-
3. **Implementation**: Write new features
|
|
468
|
-
4. **Testing**: Create test cases
|
|
469
|
-
5. **Documentation**: Generate docs
|
|
470
|
-
|
|
471
|
-
```
|
|
472
|
-
You: Let's review and improve this API endpoint:
|
|
473
|
-
/include api_endpoint.py
|
|
474
|
-
|
|
475
|
-
AI: I'll review this endpoint for potential improvements...
|
|
476
|
-
|
|
477
|
-
You: It's running slowly, can you identify bottlenecks?
|
|
478
|
-
AI: I see several performance issues...
|
|
479
|
-
|
|
480
|
-
You: Help me optimize the database queries
|
|
481
|
-
AI: Here are optimized versions of your queries...
|
|
482
|
-
|
|
483
|
-
You: Generate unit tests for the optimized version
|
|
484
|
-
AI: Here are comprehensive unit tests...
|
|
485
|
-
```
|
|
486
|
-
|
|
487
|
-
## Customization and Configuration
|
|
488
|
-
|
|
489
|
-
### Chat-Specific Configuration
|
|
490
|
-
|
|
491
|
-
Chat mode uses the same configuration as regular AIA usage. Relevant settings in `~/.config/aia/aia.yml`:
|
|
492
|
-
|
|
493
|
-
```yaml
|
|
494
|
-
# Model selection
|
|
495
|
-
models:
|
|
496
|
-
- name: gpt-4o
|
|
497
|
-
|
|
498
|
-
# LLM parameters
|
|
499
|
-
llm:
|
|
500
|
-
temperature: 0.7
|
|
501
|
-
max_tokens: 2048
|
|
502
|
-
|
|
503
|
-
# Audio for --speak and /say directive
|
|
504
|
-
audio:
|
|
505
|
-
voice: ~ # macOS system default; set e.g. "Samantha" to pick a voice
|
|
506
|
-
speak_command: say # macOS local TTS; use ~/.config/aia/tts.sh for OpenAI TTS
|
|
507
|
-
```
|
|
508
|
-
|
|
509
|
-
Start chat with specific options via CLI:
|
|
510
|
-
|
|
511
|
-
```bash
|
|
512
|
-
aia --chat --model gpt-4o --tools ./tools/ my_system_prompt
|
|
513
|
-
aia --chat --output conversation.md my_prompt # Save output
|
|
514
|
-
```
|
|
515
|
-
|
|
516
|
-
### Using Tools in Chat
|
|
517
|
-
|
|
518
|
-
Load custom RubyLLM tools into chat sessions:
|
|
519
|
-
|
|
520
|
-
```bash
|
|
521
|
-
# Load tools into a chat session
|
|
522
|
-
aia --chat --tools ./tools/file_analyzer.rb my_prompt
|
|
523
|
-
|
|
524
|
-
# Load tools from a directory
|
|
525
|
-
aia --chat --tools ./tools/ my_prompt
|
|
526
|
-
```
|
|
527
|
-
|
|
528
|
-
The AI model can call these tools during the conversation when relevant. See [Tools Guide](tools.md) for details on creating tools.
|
|
529
|
-
|
|
530
|
-
## Token Usage and Cost Tracking
|
|
531
|
-
|
|
532
|
-
### Displaying Token Usage
|
|
533
|
-
Use the `--tokens` flag to see token usage after each response:
|
|
534
|
-
|
|
535
|
-
```bash
|
|
536
|
-
# Enable token usage display
|
|
537
|
-
aia --chat --tokens
|
|
538
|
-
|
|
539
|
-
# Example output after a response:
|
|
540
|
-
# AI: Here's my response to your question...
|
|
541
|
-
#
|
|
542
|
-
# Tokens: input=125, output=89, model=gpt-4o-mini
|
|
543
|
-
```
|
|
544
|
-
|
|
545
|
-
### Cost Estimation
|
|
546
|
-
Use the `--cost` flag to include cost calculations with token usage:
|
|
547
|
-
|
|
548
|
-
```bash
|
|
549
|
-
# Enable cost estimation (automatically enables --tokens)
|
|
550
|
-
aia --chat --cost
|
|
551
|
-
|
|
552
|
-
# Example output after a response:
|
|
553
|
-
# AI: Here's my response to your question...
|
|
554
|
-
#
|
|
555
|
-
# Tokens: input=125, output=89, model=gpt-4o-mini
|
|
556
|
-
# Cost: $0.0003 (input: $0.0002, output: $0.0001)
|
|
557
|
-
```
|
|
558
|
-
|
|
559
|
-
### Multi-Model Token Tracking
|
|
560
|
-
When using multiple models, token usage is displayed for each model:
|
|
561
|
-
|
|
562
|
-
```bash
|
|
563
|
-
aia --chat --tokens --model gpt-4,claude-3-sonnet
|
|
564
|
-
|
|
565
|
-
# Example output:
|
|
566
|
-
# from: gpt-4
|
|
567
|
-
# Here's my response...
|
|
568
|
-
#
|
|
569
|
-
# from: claude-3-sonnet
|
|
570
|
-
# Here's my alternative response...
|
|
571
|
-
#
|
|
572
|
-
# Model: gpt-4 - Tokens: input=125, output=89
|
|
573
|
-
# Model: claude-3-sonnet - Tokens: input=125, output=112
|
|
574
|
-
```
|
|
575
|
-
|
|
576
|
-
## Troubleshooting Chat Mode
|
|
577
|
-
|
|
578
|
-
### Common Issues
|
|
579
|
-
|
|
580
|
-
#### Context Too Long
|
|
581
|
-
```
|
|
582
|
-
Error: Context exceeds maximum length
|
|
583
|
-
```
|
|
584
|
-
**Solution**: Use `/clear` to clear history or `/context trim` to keep recent messages only.
|
|
585
|
-
|
|
586
|
-
#### Model Not Responding
|
|
587
|
-
```
|
|
588
|
-
Error: Model timeout or connection error
|
|
589
|
-
```
|
|
590
|
-
**Solution**: Check your internet connection and API keys, try switching models.
|
|
591
|
-
|
|
592
|
-
#### Tool Not Found
|
|
593
|
-
```
|
|
594
|
-
Error: Tool 'my_tool' not found
|
|
595
|
-
```
|
|
596
|
-
**Solution**: Verify tool paths with `/tools` and check tool file syntax.
|
|
597
|
-
|
|
598
|
-
### Performance Optimization
|
|
599
|
-
|
|
600
|
-
#### Reduce Token Usage
|
|
601
|
-
- Clear context regularly with `/clear`
|
|
602
|
-
- Use shorter, more focused messages
|
|
603
|
-
- Summarize long conversations periodically
|
|
604
|
-
|
|
605
|
-
#### Improve Response Speed
|
|
606
|
-
- Use faster models for simple queries
|
|
607
|
-
- Cache frequently used context
|
|
608
|
-
- Optimize tool implementations
|
|
609
|
-
|
|
610
|
-
#### Memory Management
|
|
611
|
-
```bash
|
|
612
|
-
# Monitor memory usage
|
|
613
|
-
aia --chat --debug --verbose
|
|
614
|
-
|
|
615
|
-
# Use memory-efficient models
|
|
616
|
-
aia --chat --model gpt-3.5-turbo
|
|
617
|
-
```
|
|
618
|
-
|
|
619
|
-
## Best Practices
|
|
620
|
-
|
|
621
|
-
### Effective Chat Techniques
|
|
622
|
-
1. **Be Specific**: Clear, detailed questions get better responses
|
|
623
|
-
2. **Provide Context**: Include relevant information upfront
|
|
624
|
-
3. **Iterate**: Build on previous responses for deeper insights
|
|
625
|
-
4. **Use Tools**: Leverage tools for data processing and analysis
|
|
626
|
-
5. **Save Progress**: Regular saves prevent loss of valuable insights
|
|
627
|
-
|
|
628
|
-
### Security Considerations
|
|
629
|
-
1. **Code Execution Directives**: `/ruby` executes arbitrary Ruby code and `/shell` runs system commands with your user permissions. Only use trusted prompts containing these directives
|
|
630
|
-
2. **Sensitive Data**: Avoid sharing confidential information in prompts or chat
|
|
631
|
-
3. **Tool Access**: Restrict tool permissions with `--allowed-tools` and `--rejected-tools`
|
|
632
|
-
4. **MCP Servers**: Control which MCP servers can run with `--mcp-use` and `--mcp-skip`
|
|
633
|
-
5. **Session Management**: Clear sensitive conversations with `/clear`
|
|
634
|
-
6. **API Keys**: Keep credentials secure; never embed them in prompt files
|
|
635
|
-
|
|
636
|
-
### Productivity Tips
|
|
637
|
-
1. **Keyboard Shortcuts**: Learn and use available shortcuts
|
|
638
|
-
2. **Template Messages**: Create reusable message templates
|
|
639
|
-
3. **Model Selection**: Choose appropriate models for different tasks
|
|
640
|
-
4. **Batch Operations**: Process multiple items in single conversations
|
|
641
|
-
|
|
642
|
-
## Integration with Other AIA Features
|
|
643
|
-
|
|
644
|
-
### Pipeline Integration
|
|
645
|
-
```bash
|
|
646
|
-
# Start chat after pipeline completion
|
|
647
|
-
aia --pipeline "data_prep,analysis" --chat dataset.csv
|
|
648
|
-
|
|
649
|
-
# Process results in chat mode
|
|
650
|
-
```
|
|
651
|
-
|
|
652
|
-
### Configuration Integration
|
|
653
|
-
```bash
|
|
654
|
-
# Use predefined configurations in chat
|
|
655
|
-
aia --config-file chat_setup.yml --chat
|
|
656
|
-
|
|
657
|
-
# Override specific settings
|
|
658
|
-
aia --chat --temperature 0.9 --max-tokens 3000
|
|
659
|
-
```
|
|
660
|
-
|
|
661
|
-
### Output Integration
|
|
662
|
-
```bash
|
|
663
|
-
# Save chat output to file
|
|
664
|
-
aia --chat --output discussion.md --markdown
|
|
665
|
-
|
|
666
|
-
# Append to existing files
|
|
667
|
-
aia --chat --output project_log.md --append
|
|
668
|
-
```
|
|
669
|
-
|
|
670
|
-
## Related Documentation
|
|
671
|
-
|
|
672
|
-
- [Getting Started](getting-started.md) - Basic AIA usage
|
|
673
|
-
- [Working with Models](models.md) - Model selection and configuration
|
|
674
|
-
- [Tools Integration](tools.md) - Using and creating tools
|
|
675
|
-
- [CLI Reference](../cli-reference.md) - Command-line options
|
|
676
|
-
- [Configuration](../configuration.md) - Setup and customization
|
|
677
|
-
|
|
678
|
-
---
|
|
679
|
-
|
|
680
|
-
Chat mode is one of AIA's most powerful features. Experiment with different models, tools, and workflows to find what works best for your use cases!
|