aia 0.9.19 → 0.9.20

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.
Files changed (14) hide show
  1. checksums.yaml +4 -4
  2. data/.version +1 -1
  3. data/CHANGELOG.md +151 -91
  4. data/README.md +128 -3
  5. data/docs/cli-reference.md +71 -4
  6. data/docs/guides/models.md +196 -1
  7. data/lib/aia/config/base.rb +6 -1
  8. data/lib/aia/config/cli_parser.rb +116 -2
  9. data/lib/aia/config/file_loader.rb +33 -1
  10. data/lib/aia/prompt_handler.rb +22 -1
  11. data/lib/aia/ruby_llm_adapter.rb +134 -30
  12. data/lib/aia/session.rb +24 -8
  13. data/lib/aia/utility.rb +19 -1
  14. metadata +1 -1
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 8fb298b4e9a1ddc4748425decde69e1c11d8e7eb195cf264b918c4d69bf64e01
4
- data.tar.gz: a0cffea9fec68a81fbe5e5d36fed20255e33c1d230ec0dd518e08ad7adc56afa
3
+ metadata.gz: 24f8a994c526c8cd4cbd1c90e0fa6d1d9139584ed71b160693d3d62c6d990d8a
4
+ data.tar.gz: acf5c080b79e7c9d87770bfefe126cf455ea5d2e334766caa95348ced43e1420
5
5
  SHA512:
6
- metadata.gz: 6076117839c543fda6756e6657f69d9c35fb561213697e464701eb1515a1d38cff130e7cc57159bf44a8586387144257887906e2ffc63cf183886e816cfd6b84
7
- data.tar.gz: 42a6d282bcf587edf84e0db8d13998e0f233f9a66f52977cbaa2d0c152d44e7691207a48a8bec68800e18b1abe81bd2964d841c29eca7437a69f91a2febfd67b
6
+ metadata.gz: c454d06e3f5bda976e7efdfe7967931045afaced2b4b68fdd9cd8c1d0c7ab02e702a8c49e62391f16e96624bea154b404a48afcafdae6aaadbae02af56a852ed
7
+ data.tar.gz: 4c0b17155f9b088611a8b24cd6fdaa5873916ba3392d61b2a0c7eca62d18644b5e0349d9a721d3d7b9470d37eb09117ed5a92c546083c5e93eb4358431296a83
data/.version CHANGED
@@ -1 +1 @@
1
- 0.9.19
1
+ 0.9.20
data/CHANGELOG.md CHANGED
@@ -1,14 +1,78 @@
1
1
  # Changelog
2
2
  ## [Unreleased]
3
3
 
4
- ### [0.9.19] 2025-10-06
5
-
6
- #### Bug Fixes
4
+ ## [0.9.20] 2025-10-06
5
+ ### Added
6
+ - **Enhanced Multi-Model Role System (ADR-005)**: Implemented per-model role assignment with inline syntax
7
+ - New inline syntax: `--model MODEL[=ROLE][,MODEL[=ROLE]]...`
8
+ - Example: `aia --model gpt-4o=architect,claude=security,gemini=performance design_doc.md`
9
+ - Support for duplicate models with different roles: `gpt-4o=optimist,gpt-4o=pessimist,gpt-4o=realist`
10
+ - Added `--list-roles` command to discover available role files
11
+ - Display format shows instance numbers and roles: `gpt-4o #1 (optimist):`, `gpt-4o #2 (pessimist):`
12
+ - Consensus mode drops role for neutral synthesis
13
+ - Chat mode roles are immutable during session
14
+ - Nested role path support: `--model gpt-4o=specialized/architect`
15
+ - Full backward compatibility with existing `--role` flag
16
+
17
+ - **Config File Model Roles Support (ADR-005 v2)**:
18
+ - Enhanced `model` key in config files to support array of hashes with roles
19
+ - Format: `model: [{model: gpt-4o, role: architect}, {model: claude, role: security}]`
20
+ - Mirrors internal data structure (array of hashes with `model`, `role`, `instance`, `internal_id`)
21
+ - Supports models without roles: `model: [{model: gpt-4o}]`
22
+ - Enables reusable model-role setups across sessions
23
+ - Configuration precedence: CLI inline > CLI flag > Environment variable > Config file
24
+
25
+ - **Environment Variable Inline Syntax (ADR-005 v2)**:
26
+ - Added support for inline role syntax in `AIA_MODEL` environment variable
27
+ - Example: `export AIA_MODEL="gpt-4o=architect,claude=security,gemini=performance"`
28
+ - Maintains backward compatibility with simple comma-separated model lists
29
+ - Detects `=` to distinguish between formats
30
+
31
+ ### Bug Fixes
32
+ - **Multi-Model Chat Cross-Talk**: Fixed bug where model instances with different roles could see each other's conversation history
33
+ - Updated Session to properly extract `internal_id` from hash-based model specs (lib/aia/session.rb:47-68)
34
+ - Fixed `parse_multi_model_response` to normalize display names to internal IDs (lib/aia/session.rb:538-570)
35
+ - Each model instance now maintains completely isolated conversation context
36
+ - Fixes issue where models would respond as if aware of other models' perspectives
37
+
38
+ ### Improvements
39
+ - **Robot ASCII Display**: Updated `robot` method to extract and display only model names from new hash format (lib/aia/utility.rb:24-53)
40
+ - Handles string, array of strings, and array of hashes formats
41
+ - Shows clean model list: "gpt-4o, claude, gemini" instead of hash objects
42
+
43
+ ### Testing
44
+ - Added comprehensive test suite for config file and environment variable model roles
45
+ - test/aia/config_model_roles_test.rb: 8 tests covering array processing, env var parsing, YAML config files
46
+ - Added 15 tests for role parsing with inline syntax (test/aia/role_parsing_test.rb)
47
+ - Fixed Mocha test cleanup in multi_model_isolation_test.rb
48
+ - Full test suite: 306 runs, 980 assertions, 0 failures (1 pre-existing Mocha isolation issue)
49
+
50
+ ### Technical Implementation
51
+ - Modified `config.model` to support array of hashes with model metadata: `{model:, role:, instance:, internal_id:}`
52
+ - Added `parse_models_with_roles` method with fail-fast validation (lib/aia/config/cli_parser.rb)
53
+ - Added `validate_role_exists` with helpful error messages showing available roles
54
+ - Added `list_available_roles` and `list_available_role_names` methods for role discovery
55
+ - Added `load_role_for_model` method to PromptHandler for per-model role loading (lib/aia/prompt_handler.rb)
56
+ - Enhanced RubyLLMAdapter to handle hash-based model specs and prepend roles per model
57
+ - Added `extract_model_names` to extract model names from specs
58
+ - Added `get_model_spec` to retrieve full spec by internal_id
59
+ - Added `prepend_model_role` to inject role content into prompts
60
+ - Added `format_model_display_name` for consistent display formatting
61
+ - Updated Session initialization to handle hash-based model specs for context managers
62
+ - Updated display formatting to show instance numbers and roles
63
+ - Maintained backward compatibility with string/array model configurations
64
+ - Added `process_model_array_with_roles` method in FileLoader (lib/aia/config/file_loader.rb:91-116)
65
+ - Enhanced `apply_file_config_to_struct` to detect and process model arrays with role hashes
66
+ - Enhanced `envar_options` to parse inline syntax for `:model` key (lib/aia/config/base.rb:212-217)
67
+
68
+ ## [0.9.19] 2025-10-06
69
+
70
+ ### Bug Fixes
7
71
  - **CRITICAL BUG FIX**: Fixed multi-model cross-talk issue (#118) where models could see each other's conversation history
8
72
  - **BUG FIX**: Implemented complete two-level context isolation to prevent models from contaminating each other's responses
9
73
  - **BUG FIX**: Fixed token count inflation caused by models processing combined conversation histories
10
74
 
11
- #### Technical Changes
75
+ ### Technical Changes
12
76
  - **Level 1 (Library)**: Implemented per-model RubyLLM::Context isolation - each model now has its own Context instance (lib/aia/ruby_llm_adapter.rb)
13
77
  - **Level 2 (Application)**: Implemented per-model ContextManager isolation - each model maintains its own conversation history (lib/aia/session.rb)
14
78
  - Added `parse_multi_model_response` method to extract individual model responses from combined output (lib/aia/session.rb:502-533)
@@ -23,17 +87,17 @@
23
87
  - Added comprehensive test coverage with 6 new tests for multi-model isolation
24
88
  - Updated LocalProvidersTest to reflect Context-based architecture
25
89
 
26
- #### Architecture
90
+ ### Architecture
27
91
  - **ADR-002-revised**: Complete Multi-Model Isolation (see `.architecture/decisions/adrs/ADR-002-revised-multi-model-isolation.md`)
28
92
  - Eliminated global state dependencies in multi-model chat sessions
29
93
  - Maintained backward compatibility with single-model mode (verified with tests)
30
94
 
31
- #### Test Coverage
95
+ ### Test Coverage
32
96
  - Added `test/aia/multi_model_isolation_test.rb` with comprehensive isolation tests
33
97
  - Tests cover: response parsing, per-model context managers, single-model compatibility, RubyLLM::Context isolation
34
98
  - Full test suite: 282 runs, 837 assertions, 0 failures, 0 errors, 13 skips ✅
35
99
 
36
- #### Expected Behavior After Fix
100
+ ### Expected Behavior After Fix
37
101
  Previously, when running multi-model chat with repeated prompts:
38
102
  - ❌ Models would see BOTH their own AND other models' responses
39
103
  - ❌ Models would report inflated counts (e.g., "5 times", "6 times" instead of "3 times")
@@ -44,7 +108,7 @@ Now with the fix:
44
108
  - ✅ Each model correctly reports its own interaction count
45
109
  - ✅ Token counts accurately reflect per-model conversation size
46
110
 
47
- #### Usage Examples
111
+ ### Usage Examples
48
112
  ```bash
49
113
  # Multi-model chat now properly isolates each model's context
50
114
  bin/aia --chat --model lms/openai/gpt-oss-20b,ollama/gpt-oss:20b --metrics
@@ -64,47 +128,47 @@ bin/aia --chat --model lms/openai/gpt-oss-20b,ollama/gpt-oss:20b --metrics
64
128
  # (Previously: LMS would say "5 times", Ollama "6 times" due to cross-talk)
65
129
  ```
66
130
 
67
- ### [0.9.18] 2025-10-05
131
+ ## [0.9.18] 2025-10-05
68
132
 
69
- #### Bug Fixes
133
+ ### Bug Fixes
70
134
  - **BUG FIX**: Fixed RubyLLM provider error parsing to handle both OpenAI and LM Studio error formats
71
135
  - **BUG FIX**: Fixed "String does not have #dig method" errors when parsing error responses from local providers
72
136
  - **BUG FIX**: Enhanced error parsing to gracefully handle malformed JSON responses
73
137
 
74
- #### Improvements
138
+ ### Improvements
75
139
  - **ENHANCEMENT**: Removed debug output statements from RubyLLMAdapter for cleaner production logs
76
140
  - **ENHANCEMENT**: Improved error handling with debug logging for JSON parsing failures
77
141
 
78
- #### Documentation
142
+ ### Documentation
79
143
  - **DOCUMENTATION**: Added Local Models entry to MkDocs navigation for better documentation accessibility
80
144
 
81
- #### Technical Changes
145
+ ### Technical Changes
82
146
  - Enhanced provider_fix extension to support multiple error response formats (lib/extensions/ruby_llm/provider_fix.rb)
83
147
  - Cleaned up debug puts statements from RubyLLMAdapter and provider_fix
84
148
  - Added robust JSON parsing with fallback error handling
85
149
 
86
- ### [0.9.17] 2025-10-04
150
+ ## [0.9.17] 2025-10-04
87
151
 
88
- #### New Features
152
+ ### New Features
89
153
  - **NEW FEATURE**: Enhanced local model support with comprehensive validation and error handling
90
154
  - **NEW FEATURE**: Added `lms/` prefix support for LM Studio models with automatic validation against loaded models
91
155
  - **NEW FEATURE**: Enhanced `//models` directive to auto-detect and display local providers (Ollama and LM Studio)
92
156
  - **NEW FEATURE**: Added model name prefix display in error messages for LM Studio (`lms/` prefix)
93
157
 
94
- #### Improvements
158
+ ### Improvements
95
159
  - **ENHANCEMENT**: Improved LM Studio integration with model validation against `/v1/models` endpoint
96
160
  - **ENHANCEMENT**: Enhanced error messages showing exact model names with correct prefixes when validation fails
97
161
  - **ENHANCEMENT**: Added environment variable support for custom LM Studio API base (`LMS_API_BASE`)
98
162
  - **ENHANCEMENT**: Improved `//models` directive output formatting for local models with size and modified date for Ollama
99
163
  - **ENHANCEMENT**: Enhanced multi-model support to seamlessly mix local and cloud models
100
164
 
101
- #### Documentation
165
+ ### Documentation
102
166
  - **DOCUMENTATION**: Added comprehensive local model documentation to README.md
103
167
  - **DOCUMENTATION**: Created new docs/guides/local-models.md guide covering Ollama and LM Studio setup, usage, and troubleshooting
104
168
  - **DOCUMENTATION**: Updated docs/guides/models.md with local provider sections including comparison table and workflow examples
105
169
  - **DOCUMENTATION**: Enhanced docs/faq.md with 5 new FAQ entries covering local model usage, differences, and error handling
106
170
 
107
- #### Technical Changes
171
+ ### Technical Changes
108
172
  - Enhanced RubyLLMAdapter with LM Studio model validation (lib/aia/ruby_llm_adapter.rb)
109
173
  - Updated models directive to query local provider endpoints (lib/aia/directives/models.rb)
110
174
  - Added provider_fix extension for RubyLLM compatibility (lib/extensions/ruby_llm/provider_fix.rb)
@@ -112,12 +176,12 @@ bin/aia --chat --model lms/openai/gpt-oss-20b,ollama/gpt-oss:20b --metrics
112
176
  - Updated dependencies: ruby_llm, webmock, crack, rexml
113
177
  - Bumped Ruby bundler version to 2.7.2
114
178
 
115
- #### Bug Fixes
179
+ ### Bug Fixes
116
180
  - **BUG FIX**: Fixed missing `lms/` prefix in LM Studio model listings
117
181
  - **BUG FIX**: Fixed model validation error messages to show usable model names with correct prefixes
118
182
  - **BUG FIX**: Fixed Ollama endpoint to use native API (removed incorrect `/v1` suffix)
119
183
 
120
- #### Usage Examples
184
+ ### Usage Examples
121
185
  ```bash
122
186
  # Use LM Studio with validation
123
187
  aia --model lms/qwen/qwen3-coder-30b my_prompt
@@ -133,75 +197,74 @@ aia --model ollama/llama3.2 --chat
133
197
  > //models
134
198
  ```
135
199
 
136
- ### [0.9.16] 2025-09-26
200
+ ## [0.9.16] 2025-09-26
137
201
 
138
- #### New Features
202
+ ### New Features
139
203
  - **NEW FEATURE**: Added support for Ollama AI provider
140
204
  - **NEW FEATURE**: Added support for Osaurus AI provider
141
205
  - **NEW FEATURE**: Added support for LM Studio AI provider
142
206
 
143
- #### Improvements
207
+ ### Improvements
144
208
  - **ENHANCEMENT**: Expanded AI provider ecosystem with three new local/self-hosted model options
145
209
  - **ENHANCEMENT**: Improved flexibility for users preferring local LLM deployments
146
210
 
147
- ## Released
148
- ### [0.9.15] 2025-09-21
211
+ ## [0.9.15] 2025-09-21
149
212
 
150
- #### New Features
213
+ ### New Features
151
214
  - **NEW FEATURE**: Added `//paste` directive to insert clipboard contents into prompts
152
215
  - **NEW FEATURE**: Added `//clipboard` alias for the paste directive
153
216
 
154
- #### Technical Changes
217
+ ### Technical Changes
155
218
  - Enhanced DirectiveProcessor with clipboard integration using the clipboard gem
156
219
  - Added comprehensive test coverage for paste directive functionality
157
220
 
158
- ### [0.9.14] 2025-09-19
221
+ ## [0.9.14] 2025-09-19
159
222
 
160
- #### New Features
223
+ ### New Features
161
224
  - **NEW FEATURE**: Added `//checkpoint` directive to create named snapshots of conversation context
162
225
  - **NEW FEATURE**: Added `//restore` directive to restore context to a previous checkpoint
163
226
  - **NEW FEATURE**: Enhanced `//context` (and `//review`) directive to display checkpoint markers in conversation history
164
227
  - **NEW FEATURE**: Added `//cp` alias for checkpoint directive
165
228
 
166
- #### Improvements
229
+ ### Improvements
167
230
  - **ENHANCEMENT**: Context manager now tracks checkpoint positions for better context visualization
168
231
  - **ENHANCEMENT**: Checkpoint system uses auto-incrementing integer names when no name is provided
169
232
  - **ENHANCEMENT**: Restore directive defaults to last checkpoint when no name specified
170
233
  - **ENHANCEMENT**: Clear context now also clears all checkpoints
171
234
 
172
- #### Bug Fixes
235
+ ### Bug Fixes
173
236
  - **BUG FIX**: Fixed `//help` directive that was showing empty list of directives
174
237
  - **BUG FIX**: Help directive now displays all directives from all registered modules
175
238
  - **BUG FIX**: Help directive now shows proper descriptions and aliases for all directives
176
239
  - **BUG FIX**: Help directive organizes directives by category for better readability
177
240
 
178
- #### Technical Changes
241
+ ### Technical Changes
179
242
  - Enhanced ContextManager with checkpoint storage and restoration capabilities
180
243
  - Added checkpoint_positions method to track checkpoint locations in context
181
244
  - Refactored help directive to collect directives from all registered modules
182
245
  - Added comprehensive test coverage for checkpoint and restore functionality
183
246
 
184
- ### [0.9.13] 2025-09-02
185
- #### New Features
247
+ ## [0.9.13] 2025-09-02
248
+ ### New Features
186
249
  - **NEW FEATURE**: Added `--metrics` flag to show token counts for each model
187
250
  - **NEW FEATURE**: Added `--cost` flag to enable cost estimation for each model
188
251
 
189
- #### Improvements
252
+ ### Improvements
190
253
  - **DEPENDENCY**: Removed versionaire dependency, simplifying version management
191
254
  - **ENHANCEMENT**: Improved test suite reliability and coverage
192
255
  - **ENHANCEMENT**: Updated Gemfile.lock with latest dependency versions
193
256
 
194
- #### Bug Fixes
257
+ ### Bug Fixes
195
258
  - **BUG FIX**: Fixed version handling issues by removing external versioning dependency
196
259
 
197
- #### Technical Changes
260
+ ### Technical Changes
198
261
  - Simplified version management by removing versionaire gem
199
262
  - Enhanced test suite with improved assertions and coverage
200
263
  - Updated various gem dependencies to latest stable versions
201
264
 
202
- ### [0.9.12] 2025-08-28
265
+ ## [0.9.12] 2025-08-28
203
266
 
204
- #### New Features
267
+ ### New Features
205
268
  - **MAJOR NEW FEATURE**: Multi-model support - specify multiple AI models simultaneously with comma-separated syntax
206
269
  - **NEW FEATURE**: `--consensus` flag to enable primary model consensus mode for synthesized responses from multiple models
207
270
  - **NEW FEATURE**: `--no-consensus` flag to explicitly force individual responses from all models
@@ -212,21 +275,21 @@ aia --model ollama/llama3.2 --chat
212
275
  - **NEW FEATURE**: Multi-model support in both batch and interactive chat modes
213
276
  - **NEW FEATURE**: Comprehensive documentation website https://madbomber.github.io/aia/
214
277
 
215
- #### Improvements
278
+ ### Improvements
216
279
  - **ENHANCEMENT**: Enhanced `//model` directive output with detailed multi-model configuration display
217
280
  - **ENHANCEMENT**: Improved error handling with graceful fallback when model initialization fails
218
281
  - **ENHANCEMENT**: Better TTY handling in chat mode to prevent `Errno::ENXIO` errors in containerized environments
219
282
  - **ENHANCEMENT**: Updated directive processor to use new module-based architecture for better maintainability
220
283
  - **ENHANCEMENT**: Improved batch mode output file formatting consistency between STDOUT and file output
221
284
 
222
- #### Bug Fixes
285
+ ### Bug Fixes
223
286
  - **BUG FIX**: Fixed DirectiveProcessor TypeError that prevented application startup with invalid directive calls
224
287
  - **BUG FIX**: Fixed missing primary model output in batch mode output files
225
288
  - **BUG FIX**: Fixed inconsistent formatting between STDOUT and file output in batch mode
226
289
  - **BUG FIX**: Fixed TTY availability issues in chat mode for containerized environments
227
290
  - **BUG FIX**: Fixed directive processing to use updated module-based registry system
228
291
 
229
- #### Technical Changes
292
+ ### Technical Changes
230
293
  - Fixed ruby_llm version to 1.5.1
231
294
  - Added extra API_KEY configuration for new LLM providers
232
295
  - Updated RubyLLMAdapter to support multiple model initialization and management
@@ -235,13 +298,13 @@ aia --model ollama/llama3.2 --chat
235
298
  - Updated CLI parser to support multi-model flags and options
236
299
  - Enhanced configuration system to support consensus mode settings
237
300
 
238
- #### Documentation
301
+ ### Documentation
239
302
  - **DOCUMENTATION**: Comprehensive README.md updates with multi-model usage examples and best practices
240
303
  - **DOCUMENTATION**: Added multi-model section to README with detailed usage instructions
241
304
  - **DOCUMENTATION**: Updated command-line options table with new multi-model flags
242
305
  - **DOCUMENTATION**: Added practical multi-model examples for decision-making scenarios
243
306
 
244
- #### Usage Examples
307
+ ### Usage Examples
245
308
  ```bash
246
309
  # Basic multi-model usage
247
310
  aia my_prompt -m gpt-4o-mini,gpt-3.5-turbo
@@ -256,25 +319,25 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
256
319
  //model # Use in any prompt or chat session
257
320
  ```
258
321
 
259
- #### Migration Notes
322
+ ### Migration Notes
260
323
  - Existing single-model usage remains unchanged and fully compatible
261
324
  - Multi-model is opt-in via comma-separated model names
262
325
  - Default behavior without `--consensus` flag shows individual responses from all models
263
326
  - Invalid model names are reported but don't prevent valid models from working
264
327
 
265
- #### TODO
328
+ ### TODO
266
329
  - TODO: focus on log file consistency using Logger
267
330
 
268
331
 
269
- ### [0.9.11] 2025-07-31
332
+ ## [0.9.11] 2025-07-31
270
333
  - added a cost per 1 million input tokens to available_models query output
271
334
  - updated ruby_llm to version 1.4.0
272
335
  - updated all other gem dependencies to their latest versions
273
336
 
274
- ### [0.9.10] 2025-07-18
337
+ ## [0.9.10] 2025-07-18
275
338
  - updated ruby_llm-mcp to version 0.6.1 which solves problems with MCP tools not being installed
276
339
 
277
- ### [0.9.9] 2025-07-10
340
+ ## [0.9.9] 2025-07-10
278
341
  - refactored the Session and Config classes into more testable method_missing
279
342
  - updated the test suire for both the Session and Config classes
280
343
  - added support for MCP servers coming into AIA via the shared_tools gem
@@ -285,13 +348,13 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
285
348
  - //available_models now has context window size and capabilities for each model returned
286
349
 
287
350
 
288
- ### [0.9.8] 2025-06-25
351
+ ## [0.9.8] 2025-06-25
289
352
  - fixing an issue with pipelined prompts
290
353
  - now showing the complete modality of the model on the processing line.
291
354
  - changed -p option from prompts_dir to pipeline
292
355
  - found problem with simple cov and deep cov w/r/t their reported test coverage; they have problems with heredoc and complex conditionals.
293
356
 
294
- ### [0.9.7] 2025-06-20
357
+ ## [0.9.7] 2025-06-20
295
358
 
296
359
  - **NEW FEATURE**: Added `--available_models` CLI option to list all available AI models
297
360
  - **NEW FEATURE**: Added `//tools` to show a list of available tools and their description
@@ -302,7 +365,7 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
302
365
  - **DOCUMENTATION**: Updated README for better clarity and structure
303
366
  - **DEPENDENCY**: Updated Gemfile.lock with latest dependency versions
304
367
 
305
- ### [0.9.6] 2025-06-13
368
+ ## [0.9.6] 2025-06-13
306
369
  - fixed issue 84 with the //llms directive
307
370
  - changed the monkey patch to the RubyLLM::Model::Modalities class at the suggestions of the RubyLLM author in prep for a PR against that gem.
308
371
  - added the shared_tools gem - need to add examples on how to use it with the --tools option
@@ -310,11 +373,11 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
310
373
  - added images/aia.png to README.md
311
374
  - let claude code rewrite the README.md file. Some details were dropped but overall in reads better. Need to add the details to a wiki or other documentation site.
312
375
 
313
- ### [0.9.5] 2025-06-04
376
+ ## [0.9.5] 2025-06-04
314
377
  - changed the RubyLLM::Modalities class to use method_missing for mode query
315
378
  - hunting for why the //llms query directive is not finding image_to_image LLMs.
316
379
 
317
- ### [0.9.4] 2025-06-03
380
+ ## [0.9.4] 2025-06-03
318
381
  - using RubyLLM v1.3.0
319
382
  - setting up a docs infrastructure to behave like the ruby_llm gem's guides side
320
383
  - fixed bug in the text-to-image workflow
@@ -322,7 +385,7 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
322
385
  - need to pay attention to the test suite
323
386
  - also need to ensure the non text2text modes are working
324
387
 
325
- ### [0.9.3rc1] 2025-05-24
388
+ ## [0.9.3rc1] 2025-05-24
326
389
  - using ruby_llm v1.3.0rc1
327
390
  - added a models database refresh based on integer days interval with the --refresh option
328
391
  - config file now has a "last_refresh" String in format YYYY-MM-DD
@@ -331,43 +394,41 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
331
394
  - fixed a bug in the prompt_manager gem which is now at v0.5.5
332
395
 
333
396
 
334
- ### [0.9.2] 2025-05-18
397
+ ## [0.9.2] 2025-05-18
335
398
  - removing the MCP experiment
336
399
  - adding support for RubyLLM::Tool usage in place of the MCP stuff
337
400
  - updated prompt_manager to v0.5.4 which fixed shell integration problem
338
401
 
339
- ### [0.9.1] 2025-05-16
402
+ ## [0.9.1] 2025-05-16
340
403
  - rethink MCP approach in favor of just RubyLLM::Tool
341
404
  - fixed problem with //clear
342
405
  - fixed a problem with a priming prompt in a chat loop
343
406
 
344
- ### [0.9.0] 2025-05-13
407
+ ## [0.9.0] 2025-05-13
345
408
  - Adding experimental MCP Client suppot
346
409
  - removed the CLI options --erb and --shell but kept them in the config file with a default of true for both
347
410
 
348
- ### [0.8.6] 2025-04-23
411
+ ## [0.8.6] 2025-04-23
349
412
  - Added a client adapter for the ruby_llm gem
350
413
  - Added the adapter config item and the --adapter option to select at runtime which client to use ai_client or ruby_llm
351
414
 
352
- ### [0.8.5] 2025-04-19
415
+ ## [0.8.5] 2025-04-19
353
416
  - documentation updates
354
417
  - integrated the https://pure.md web service for inserting web pages into the context window
355
418
  - //include http?://example.com/stuff
356
419
  - //webpage http?://example.com/stuff
357
420
 
358
- ### [0.8.2] 2025-04-18
421
+ ## [0.8.2] 2025-04-18
359
422
  - fixed problems with pre-loaded context and chat repl
360
423
  - piped content into `aia --chat` is now a part of the context/instructions
361
424
  - content via "aia --chat < some_file" is added to the context/instructions
362
425
  - `aia --chat context_file.txt context_file2.txt` now works
363
426
  - `aia --chat prompt_id context)file.txt` also works
364
427
 
365
-
366
-
367
- ### [0.8.1] 2025-04-17
428
+ ## [0.8.1] 2025-04-17
368
429
  - bumped version to 0.8.1 after correcting merge conflicts
369
430
 
370
- ### [0.8.0] WIP - 2025-04-15
431
+ ## [0.8.0] WIP - 2025-04-15
371
432
  - Updated PromptManager to v0.5.1 which has some of the functionality that was originally developed in the AIA.
372
433
  - Enhanced README.md to include a comprehensive table of configuration options with defaults and associated environment variables.
373
434
  - Added a note in README.md about the expandability of configuration options from a config file for dynamic prompt generation.
@@ -375,7 +436,7 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
375
436
  - Ensured version consistency across `.version`, `aia.gemspec`, and `lib/aia/version.rb`.
376
437
  - Verified and updated documentation to ensure readiness for release on RubyGems.org.
377
438
 
378
- ### [0.7.1] WIP - 2025-03-22
439
+ ## [0.7.1] WIP - 2025-03-22
379
440
  - Added `UIPresenter` class for handling user interface presentation.
380
441
  - Added `DirectiveProcessor` class for processing chat-based directives.
381
442
  - Added `HistoryManager` class for managing conversation and variable history.
@@ -389,7 +450,7 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
389
450
  - Improved error handling and user feedback for directive processing.
390
451
  - Enhanced logging and output options for chat sessions.
391
452
 
392
- ### [0.7.0] WIP - 2025-03-17
453
+ ## [0.7.0] WIP - 2025-03-17
393
454
  - Major code refactoring for better organization and maintainability:
394
455
  - Extracted `DirectiveProcessor` class to handle chat-based directives
395
456
  - Extracted `HistoryManager` class for conversation and variable history management
@@ -400,13 +461,13 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
400
461
  - Improved output handling to suppress STDOUT when chat mode is off and output file is specified
401
462
  - Updated spinner format in the process_prompt method for better user experience
402
463
 
403
- ### [0.6.?] WIP
464
+ ## [0.6.?] WIP
404
465
  - Implemented Tony Stark's Clean Slate Protocol on the develop branch
405
466
 
406
- ### [0.5.17] 2024-05-17
467
+ ## [0.5.17] 2024-05-17
407
468
  - removed replaced `semver` with `versionaire`
408
469
 
409
- ### [0.5.16] 2024-04-02
470
+ ## [0.5.16] 2024-04-02
410
471
  - fixed prompt pipelines
411
472
  - added //next and //pipeline directives as shortcuts to //config [next,pipeline]
412
473
  - Added new backend "client" as an internal OpenAI client
@@ -415,83 +476,82 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
415
476
  - Added --voice default: alloy (if "siri" and Mac? then uses cli tool "say")
416
477
  - Added --image_size and --image_quality (--is --iq)
417
478
 
418
-
419
- ### [0.5.15] 2024-03-30
479
+ ## [0.5.15] 2024-03-30
420
480
  - Added the ability to accept piped in text to be appeded to the end of the prompt text: curl $URL | aia ad_hoc
421
481
  - Fixed bugs with entering directives as follow-up prompts during a chat session
422
482
 
423
- ### [0.5.14] 2024-03-09
483
+ ## [0.5.14] 2024-03-09
424
484
  - Directly access OpenAI to do text to speech when using the `--speak` option
425
485
  - Added --voice to specify which voice to use
426
486
  - Added --speech_model to specify which TTS model to use
427
487
 
428
- ### [0.5.13] 2024-03-03
488
+ ## [0.5.13] 2024-03-03
429
489
  - Added CLI-utility `llm` as a backend processor
430
490
 
431
- ### [0.5.12] 2024-02-24
491
+ ## [0.5.12] 2024-02-24
432
492
  - Happy Birthday Ruby!
433
493
  - Added --next CLI option
434
494
  - Added --pipeline CLI option
435
495
 
436
- ### [0.5.11] 2024-02-18
496
+ ## [0.5.11] 2024-02-18
437
497
  - allow directives to return information that is inserted into the prompt text
438
498
  - added //shell command directive
439
499
  - added //ruby ruby_code directive
440
500
  - added //include path_to_file directive
441
501
 
442
- ### [0.5.10] 2024-02-03
502
+ ## [0.5.10] 2024-02-03
443
503
  - Added --roles_dir to isolate roles from other prompts if desired
444
504
  - Changed --prompts to --prompts_dir to be consistent
445
505
  - Refactored common fzf usage into its own tool class
446
506
 
447
- ### [0.5.9] 2024-02-01
507
+ ## [0.5.9] 2024-02-01
448
508
  - Added a "I'm working" spinner thing when "--verbose" is used as an indication that the backend is in the process of composing its response to the prompt.
449
509
 
450
- ### [0.5.8] 2024-01-17
510
+ ## [0.5.8] 2024-01-17
451
511
  - Changed the behavior of the --dump option. It must now be followed by path/to/file.ext where ext is a supported config file format: yml, yaml, toml
452
512
 
453
- ### [0.5.7] 2024-01-15
513
+ ## [0.5.7] 2024-01-15
454
514
  - Added ERB processing to the config_file
455
515
 
456
- ### [0.5.6] 2024-01-15
516
+ ## [0.5.6] 2024-01-15
457
517
  - Adding processing for directives, shell integration and erb to the follow up prompt in a chat session
458
518
  - some code refactoring.
459
519
 
460
520
  ## [0.5.3] 2024-01-14
461
521
  - adding ability to render markdown to the terminal using the "glow" CLI utility
462
522
 
463
- ### [0.5.2] 2024-01-13
523
+ ## [0.5.2] 2024-01-13
464
524
  - wrap response when its going to the terminal
465
525
 
466
- ### [0.5.1] 2024-01-12
526
+ ## [0.5.1] 2024-01-12
467
527
  - removed a wicked puts "loaded" statement
468
528
  - fixed missed code when the options were changed to --out_file and --log_file
469
529
  - fixed completion functions by updating $PROMPT_DIR to $AIA_PROMPTS_DIR to match the documentation.
470
530
 
471
- ### [0.5.0] 2024-01-05
531
+ ## [0.5.0] 2024-01-05
472
532
  - breaking changes:
473
533
  - changed `--config` to `--config_file`
474
534
  - changed `--env` to `--shell`
475
535
  - changed `--output` to `--out_file`
476
536
  - changed default `out_file` to `STDOUT`
477
537
 
478
- ### [0.4.3] 2023-12-31
538
+ ## [0.4.3] 2023-12-31
479
539
  - added --env to process embedded system environment variables and shell commands within a prompt.
480
540
  - added --erb to process Embedded RuBy within a prompt because have embedded shell commands will only get you in a trouble. Having ERB will really get you into trouble. Remember the simple prompt is usually the best prompt.
481
541
 
482
- ### [0.4.2] 2023-12-31
542
+ ## [0.4.2] 2023-12-31
483
543
  - added the --role CLI option to pre-pend a "role" prompt to the front of a primary prompt.
484
544
 
485
- ### [0.4.1] 2023-12-31
545
+ ## [0.4.1] 2023-12-31
486
546
  - added a chat mode
487
547
  - prompt directives now supported
488
548
  - version bumped to match the `prompt_manager` gem
489
549
 
490
- ### [0.3.20] 2023-12-28
550
+ ## [0.3.20] 2023-12-28
491
551
  - added work around to issue with multiple context files going to the `mods` backend
492
552
  - added shellwords gem to santize prompt text on the command line
493
553
 
494
- ### [0.3.19] 2023-12-26
554
+ ## [0.3.19] 2023-12-26
495
555
  - major code refactoring.
496
556
  - supports config files \*.yml, \*.yaml and \*.toml
497
557
  - usage implemented as a man page. --help will display the man page/
@@ -504,10 +564,10 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
504
564
  3. envar values over-rides ...
505
565
  4. default values
506
566
 
507
- ### [0.3.0] = 2023-11-23
567
+ ## [0.3.0] = 2023-11-23
508
568
 
509
569
  - Matching version to [prompt_manager](https://github.com/prompt_manager) This version allows for the user of history in the entery of values to prompt keywords. KW_HISTORY_MAX is set at 5. Changed CLI enteraction to use historical selection and editing of prior keyword values.
510
570
 
511
- ### [0.1.0] - 2023-11-23
571
+ ## [0.1.0] - 2023-11-23
512
572
 
513
573
  - Initial release