aia 1.1.1 → 2.0.0.0.pre.beta2

data/CHANGELOG.md

@@ -1,69 +1,283 @@
 # Changelog
+
+## [Unreleased]
+
+This section captures all changes since v1.1.0.
+
+## [2.0.0.pre.beta2] 2026-09-09
+
+Using robot_lab v0.2.5
+Using lumberjack v2.1.0
+
+### Added
+
+- **`--[no-]thinking` flag** (`lib/aia/config/cli_parser.rb`, `lib/aia/config/defaults.yml`, `lib/aia/config.rb`, `lib/aia/streaming_runner.rb`): Controls whether raw reasoning blocks from local models (e.g. `qwen3` on Ollama) are shown. Such models stream their chain-of-thought wrapped in `<think>...</think>` tags; AIA now filters these out by default so only the final answer is displayed. Pass `--thinking` to show the reasoning. The `StreamingRunner` strips the tags inline, tracking open spans across chunk boundaries. Config key: `flags.thinking` (env: `AIA_FLAGS__THINKING`); default `false`.
+
+- **Crews — every session is a team of robots** (`lib/aia/crew.rb`, `lib/aia/mention_router.rb`, `lib/aia/directives/execution_directives.rb`): Every chat session is now a crew (a `RobotLab::Network`), even with a single model; the lead robot is the **chief**.
+  - **`/add_recruit <name> [provider/model] [system prompt]`** (alias `/add`): Adds a persistent member to the crew that survives the session, shows in `/robots`, and answers to `@name`. Omit the model to inherit the chief's; use `-`/`inherit` to inherit explicitly. Recruits inherit the chief's local tools and connected MCP servers.
+  - **`/drop_recruit <name>`** (alias `/drop`): Removes a member; the chief cannot be dropped.
+  - **Skill assignment to recruits**: `/add_recruit` accepts `skill:<id>` tokens (comma-separate or repeat for several) that load named skills as the recruit's role/system prompt — letting the chief divide labor across the crew (e.g. a security reviewer + a performance reviewer). Unknown skill ids are reported rather than silently dropped. The chief's `recruit_robot` tool gained a matching `skills` param so it can assign roles itself.
+  - **`/reskill <name> [skill:<id>...] [system prompt]`**: Resets a member to a clean slate (fresh conversation) keeping its name and model, and applies a new skill/role. Backed by `Crew.reskill` and a `reskill_robot` chief tool. Useful for recovering an off-task member or moving the crew through phases.
+  - **`@crew` broadcast handle**: Sends a prompt to every member concurrently. `crew` is reserved as a member name.
+  - **Position-aware `@mention` routing**: A leading address (`@a @b ...`) runs the addressees concurrently; a `@name` woven into the body runs the members sequentially as a pipeline, sharing each reply into the others' context so later members build on earlier ones.
+  - **`/spawn` extended** to the explicit form `/spawn <name> <provider/model> <system prompt>` alongside the existing `/spawn` and `/spawn <type>` forms. `/spawn` remains a one-shot specialist for the next prompt; `/add_recruit` is its persistent counterpart.
+  - **Docs**: new [Crews guide](docs/guides/crew.md); README `@mention`/crew section and `docs/directives-reference.md` updated for `/add_recruit`, `/drop_recruit`, and the extended `/spawn`.
+
+- **`--history-file` fully implemented** (`lib/aia/ui_presenter.rb`): `chat_history_file` now checks `config.output.history_file` first — uses the configured path when set, returns `nil` when `--no-history-file` is given (disabling history). `load_chat_history` and `save_chat_history` both guard against `nil` so disabling history is a clean no-op. Resolution order: `config.output.history_file` → `paths.aia_dir/chat_history` → `~/.config/aia/chat_history`.
+
+- **`--speech-model` fully implemented** (`lib/aia/robot_factory.rb`, `lib/aia/chat_loop.rb`, `lib/aia/mention_router.rb`): `configure_audio` stores the value and passes it as the `SPEECH_MODEL` environment variable to the speak subprocess, allowing custom TTS scripts to select a model. `--voice` wires to `say -v VOICE` for the macOS `say` command.
+
+- **`--transcription-model` fully implemented** (`lib/aia/robot_factory.rb`): `configure_audio` calls `RubyLLM.configure { |c| c.default_transcription_model = ... }` so the transcription model is active for the entire session.
+
+- **`--speak-command CMD`** (`lib/aia/config/cli_parser.rb`, `lib/aia/config.rb`): New CLI option to set `audio.speak_command` at runtime without editing config. Enables full OpenAI TTS pipeline from the command line: `aia --speak --speak-command ~/.config/aia/tts.sh --speech-model tts-1-hd --voice nova my_prompt`.
+
+- **Three-stage `--speak` pipeline with per-stage spinners** (`lib/aia/chat_loop.rb`, `lib/aia/mention_router.rb`): After text streams to the terminal, `--speak` now shows distinct progress feedback for each stage — `Converting to audio...` while the TTS command runs, then `Speaking...` while the audio plays. For the local macOS `say` command (which converts and plays in one step) only `Speaking...` is shown. Custom TTS scripts receive the output file path as `$2`; AIA creates the temp file and calls `afplay` itself.
+
+- **`~/.config/aia/tts.sh`**: OpenAI TTS helper script installed at the AIA config directory. Accepts text as `$1` and output path as `$2`; reads `SPEECH_MODEL` and `AIA_AUDIO__VOICE` env vars; calls `api.openai.com/v1/audio/speech` via `curl`. Does not call `afplay` — AIA handles playback.
+
+- **`--skill` / `-s` fully implemented**: Injects skill content into the AI context; mode-aware — in `--chat` mode skills are appended to the system prompt once (persists across all turns); in pipeline mode skills are appended to each individual prompt text after the role content.
+- **`SkillUtils#skills_base_dir`**: New resolver centralising skills path computation — returns `skills.dir` when `skills_prefix` is unset, or `skills.dir / prefix` when prefix is set; shared by `SystemPromptAssembler` (chat mode) and `PipelineOrchestrator` (pipeline mode).
+- **`SkillUtils#load_skills_content` / `#load_single_skill_content`**: Load and join skill bodies from one or more skill IDs; strip YAML front matter; warn and skip missing skills without aborting.
+
+### Changed
+
+- **`skills_prefix` default changed from `"skills"` to `nil`**: When unset and no `--skills-dir` is given, the skills directory falls back to `~/.prompts/skills`; setting `--skills-prefix` appends to `--prompts-dir` (or `AIA_PROMPTS__DIR`) rather than to a fixed default.
+- **`--skills-prefix` path resolution** (`lib/aia/config/cli_parser.rb`): Three-branch logic — explicit `--skills-dir` + prefix → `skills_dir/prefix`; no `--skills-dir` but prefix set → `prompts_dir/prefix`; neither given → `AIA_SKILLS__DIR` or `~/.prompts/skills`.
+- **Docs updated for skills options**: `docs/cli-reference.md` — `--skills-prefix` default and resolution, chat-vs-pipeline injection note in `--skill`; `docs/configuration.md` — `skills_prefix` default, prompt assembly order section rewritten; `docs/directives-reference.md` — `/skill` directory resolution description.
+
+- **`.loki` asgard task runner**: Added per-project task file with quality gates (`test`, `flog`, `flay`, `rubocop`), each capturing output to `*_output.txt`; `quality` task runs all gates via `system()` and prints a per-gate pass/fail summary table; `aia` passthrough task runs `bin/aia` with arbitrary arguments from any working directory.
+- **`.rubocop.yml`**: Project-level RuboCop configuration achieving 0 offenses — disables intentional-pattern cops (`Style/FormatStringToken`, `Style/SafeNavigationChainLength`, `Lint/DuplicateBranch`), adds test-file exclusions for cops that conflict with minitest patterns, and raises Metrics thresholds to match actual method complexity.
+
+- **`LayeredOrchestrator`**: 3-tier agent orchestration — Tobor decomposes requirements, lead agents break them into specialist tasks, specialists produce artifacts. Activated via `/orchestrate`.
+- **`TaskDecomposer` + `TaskExecutor`**: Break complex prompts into parallel subtasks and execute them via TrakFlow.
+- **`OrchestratorError`, `DebateError`, `DecomposeError`**: Typed error classes for orchestration and debate failure paths (`lib/aia/errors.rb`).
+- **`tool_filter.timeout_s` config key**: Configurable TF-IDF filter timeout; defaults to 10 seconds.
+- **Parallel LLM calls**: Multi-model network turns now run concurrently via `Async::Barrier`.
+- **Session cleanup**: `at_exit` hook in `AIA.run` calls `Session#cleanup!` to release MCP connections, flush caches, and close TrakFlow.
+- **`state_setting!` DSL**: Directive subclasses declare their exclusive mode with `state_setting! :debate, :spawn, ...`; `ChatLoop` no longer maintains a hardcoded prefix list.
+- **Demo 29**: End-to-end agent harness demo building a Sinatra/Sequel application from a requirements document.
+- **`BATCH_MODE` support**: Demos 23–28 skip live `--chat` sessions when `BATCH_MODE=true`, enabling `run_all.sh` CI automation.
+
+### Changed
+
+- **TF-IDF as sole tool filter strategy**: Zvec (B), SqliteVec (C), and LSI (D) strategies removed (~2,150 LOC deleted).
+- **`auto_tool_filter` flag**: Replaces `tool_filter_a`; enabled by default; toggled via `--[no-]auto-tool-filter`.
+- **`robot_lab` dependency**: Updated from `~> 0.0.9` to `~> 0.1.0`.
+- **Lazy handler instantiation**: `SpawnHandler`, `DebateHandler`, `DelegateHandler`, and `LayeredOrchestrator` are memoized and created on first use.
+- **Lazy-require for heavy subsystems**: `VerificationNetwork`, `PromptDecomposer`, and all TrakFlow infrastructure required only when invoked.
+- **`shared_tools` optional runtime dependencies**: `dentaku`, `sequel`, and `openweathermap` moved to dev dependencies; each tool guards its `require` with a boolean constant and exposes `available?`; `bigdecimal >= 4.0` pinned conditionally for Ruby >= 4.0.
+- **`README.md`**: Added badges, "Why AIA?" feature comparison table, and Prompt Directives reorganized into seven category subsections.
+
+### Removed
+
+- **Zvec, SqliteVec, LSI tool filter strategies** and their test files.
+- **`zvec`, `sqlite-vec`, `informers` gem dependencies** from gemspec.
+- **KBS gem and rule engine**: `kbs` gem and all KBS infrastructure (RuleRouter, KBDefinitions, FactAsserter, DynamicRuleBuilder, RulesDSL, DecisionApplier, ExpertRouter) deleted.
+- **`-A`/`--tool-filter-kbs` CLI flag**, `/rules` chat directive, and user-defined rule hooks.
+- **`build_streaming_callback`**: Dead code path in `RobotFactory`.
+
+### Fixed
+
+- **`--no-mcp` flag ignored by `RobotBuilder`** (`lib/aia/robot_builder.rb`): Was directly mapping `config.mcp_servers` without checking `config.flags.no_mcp`; now delegates to `RobotFactory.mcp_server_configs(config)` which honours the flag — preventing MCP servers from connecting and tools from overflowing the model's 128-tool limit.
+- **`load_extra_config` falls through on missing file in tests** (`lib/aia/config.rb`): Restored `return` after `exit 1`; tests mock `exit` as a no-op, so without the guard the method continued to `YAML.safe_load_file` on the nonexistent path and raised `Errno::ENOENT`.
+- **`warn` → `$stderr.puts` across all lib files** (19 files): Ruby 4.0 suppresses `Kernel#warn` output by default (requires `-W` flag); messages were silently dropped — including unknown-option errors, missing-file warnings, and audio failures. Replaced all `warn` calls with `$stderr.puts` which always writes unconditionally. Test suite updated: replaced `stubs(:warn)` + `stderr_messages` patterns with `capture_io` to capture real `$stderr` output.
+- **`--speak` produced `AudioFileOpen failed` error** (`lib/aia/config/defaults.yml`, `~/.config/aia/aia.yml`): Default `speak_command` was `afplay` (an audio file player) instead of `say` (macOS TTS); passing response text to `afplay` caused it to interpret the text as a file path and fail. Default changed to `say`; `voice` and `speech_model` defaults cleared to `nil` so `say` uses the system default voice with no API call.
+
+- **`DebateHandler` convergence short-circuit** (`lib/aia/debate_handler.rb`): Added `all_signaled_convergence?` fast path — when all robots say `CONVERGED` after minimum rounds the debate ends immediately, without waiting for similarity scoring to catch up.
+- **`SpecialModeHandler` keyword argument crash** (`lib/aia/special_mode_handler.rb`): `network.run(prompt)` → `network.run(message: prompt)` to match `RobotLab::Network#run`'s keyword-only API.
+- **`ToolLoader` gem loading under Bundler** (`lib/aia/tool_loader.rb`): `Gem::LoadError` (`ScriptError`, not `StandardError`) now caught; added `eager_load_namespace_fallback` for Zeitwerk recovery; `activate_unbundled_gem` falls back to `Gem.default_dir`/`Gem.user_dir` scanning when Bundler blocks `gem name`.
+- **Demo 18 tool overload** (`examples/18_tools.sh`): Added `--allowed-tools` to expose only 3 tools; 35+ tools caused `gpt-4.1` to narrate instead of invoke.
+- **Demo 26/27 robot name** (`examples/26_debate.sh`, `examples/27_mention_routing.sh`): `RobotNamer` assigns "Vanguard" to `gpt-4.1-mini`, not "Quark"; corrected in both scripts.
+- **Ollama model tag resolution** (`lib/aia/verification_network.rb`, `lib/aia/prompt_decomposer.rb`): Pass `model.internal_id` (e.g. `ollama/qwen3:latest`) to `RobotLab.build` instead of `model.name`.
+- **Dynamic pipeline iteration** (`lib/aia/pipeline_orchestrator.rb`): Changed `config.pipeline.each` to `until config.pipeline.empty?` + `shift` so mid-run `next:`/`pipeline:` replacements are picked up immediately.
+- **AI response written to output file twice** (`lib/aia/ui_presenter.rb`): Removed file-writing from `display_ai_response`; file output exclusively owned by `output_to_file`.
+- **Unknown `@mention` falls through to broadcast** (`lib/aia/mention_router.rb`): Returns `true` and reports unrecognized names instead of silently broadcasting to all robots.
+- **Custom directive classes unavailable in ERB prompts** (`lib/aia/tool_loader.rb`): `PM::Directive.register_all` now called at the end of `ToolLoader#load_tools` so tool-provided directives are registered before the first prompt render.
+- **Demo scripts using untagged Ollama model names**: Updated to `phi4:latest` and `phi4-mini:latest`.
+- **`/ruby` directive security gate**: `eval` now guarded by `AIA.config.flags.allow_ruby_eval`.
+- **`RobotFactory` namer state leak**: `@namer` initialized once in `RobotFactory.setup` instead of reset on every robot build.
+- **`at_exit` hook registered multiple times**: Moved from `Session#start` to `AIA.run`, registered exactly once per process.
+- **GPT-5/OpenAI token parameter mismatch**: Models with `temperature: false` skip temperature; `max_tokens` translated to `max_completion_tokens` for o-series models.
+- **Installed gem BigDecimal activation conflict** (`lib/aia.rb`): AIA activates `bigdecimal >= 4.0` before loading transitive dependencies.
+- **Pipeline token metrics crash**: `display_metrics` uses `result.raw` instead of non-existent `result.output`.
+- **Skill symlink path containment**: Skill resolution checks real paths against the skills directory boundary.
+- **`--list-skills` CLI directory options**: Now honors `--prompts-dir` and `--skills-prefix` regardless of option order.
+
+### Known Issues
+
+- **`--skill` injection in RobotLab flow**: The RobotLab prompt execution path does not yet prepend configured skills to pipeline prompts and chat startup context.
+- **Path-based direct skill file restrictions**: `/skill` accepts any readable file path; should be limited to markdown files to prevent arbitrary injection.
+
 ## [1.1.1] - 2026-05-01
 
 ### Bug Fixes
-- **Conversation context lost on Ollama model pipeline steps (Issue #152)**: `maybe_change_model` was unconditionally replacing the adapter whenever the configured model name (e.g. `ollama/qwen3`) did not literally appear in the resolved model ID (`qwen3`). Fixed by stripping the provider prefix before comparison and by never replacing the adapter when conversation messages exist in any chat instance — preserving all history across pipeline steps and role changes
-- **Role file front matter overwriting active model config**: `ChatLoop#process_role_context` was allowing `fetch_role` (which calls `apply_metadata_config`) to overwrite `AIA.config.models` with any `model:` key in the role file's YAML front matter. The active model is now saved before `fetch_role` and restored afterward, so a role's front matter cannot trigger a false mismatch in `maybe_change_model`
-- **Custom `--tools` directives not available in ERB prompts**: `AIA::Directive` subclasses defined in files loaded via `--tools` were required too late — after `PromptHandler.new` had already called `register_pm_directives`. Added `require_tool_files` as the first step in `ConfigValidator#tailor` so custom directive classes are defined and registered into `PM.directives` before `PromptHandler.new` runs; `<%= timestamp %>` and other custom ERB helpers now expand correctly
-- **Demo example path resolution**: `examples/prompts_dir/project_summary` referenced `../../*.gemspec` and `../../lib/aia/*.rb`, resolving two levels above the repo root from the `examples/` working directory; corrected to `../`
+
+- **Ollama model pipeline context preservation**: Mainline fixed adapter replacement when provider-prefixed model names (for example `ollama/qwen3`) did not match resolved local model IDs, preserving conversation history across pipeline steps.
+- **Role front matter model isolation**: Mainline restored the active model after role loading so a role file's `model:` metadata cannot unexpectedly replace the configured model.
+- **Custom directive loading for ERB prompts**: Mainline loads tool files before PromptManager directive registration so directive classes provided by `--tools` are available inside ERB prompts.
+- **Demo example path resolution** (`examples/prompts_dir/project_summary`): Corrected repository-relative paths used by the example prompt.
 
 ### Improvements
-- **Demo scripts use develop-branch binary**: `examples/common.sh` now prepends `../bin` to `PATH` when the local `bin/aia` is executable, ensuring all demo scripts exercise working-tree changes rather than the installed gem
 
-### Testing
-- Added `test/aia/chat_loop_test.rb` — 6 tests covering `process_role_context`: early-return when no role configured, system message injection into chats, skipping chats that already have a system message, and model restoration after `fetch_role` side effects (Issue #152 regression tests)
-- Expanded `test/aia/chat_processor_service_test.rb` with 7 additional tests: provider-prefix stripping before model comparison, full-ID alias resolution (e.g. `claude-sonnet-4` vs `claude-sonnet-4-20250514`), adapter preservation when any chat has history, adapter replacement allowed when no history exists, and the exact Issue #152 regression scenario (OpenAI model active, role front matter specifies a Claude model)
+- **Demo scripts prefer working-tree binary** (`examples/common.sh`): Mainline demo scripts prepend `../bin` to `PATH` when local `bin/aia` is executable.
 
 ## [1.1.0] - 2026-04-23
 
 ### New Features
-- **Skills system**: Skills are subdirectories under `~/.prompts/skills` (configurable), each containing a `SKILL.md` file with YAML front matter (`name`, `description`, and any custom fields)
-  - `/skills [query]` directive lists available skills; supports positive/negative search filtering (`-term`, `~term`, `!term`)
-  - `/skill <name>` directive includes the `SKILL.md` content into the conversation; resolves by exact match then prefix match
-  - `/skill <path>` directive accepts path-based IDs (absolute, `~/`, `./`, `../`) including direct `.md` files
-  - `--list-skills` CLI flag prints all skills as markdown tables (one `## skill` heading + `| Key | Value |` table per skill, showing all front matter fields)
-  - `--skill`/`-s SKILL_IDS` CLI option prepends one or more skills to the prompt (comma-separated, repeatable); accepts skill IDs or paths
-  - `--skills-dir DIR` and `--skills-prefix PREFIX` CLI options configure the skills directory
-- **Path-based skill resolution**: `--skill` and `/skill` now accept file-system paths in addition to named IDs
-  - Absolute paths: `--skill /path/to/skill-dir` or `--skill /path/to/skill.md`
-  - Home-relative: `--skill ~/skills/my-skill`
-  - Working-directory-relative: `--skill ./temp_skill.md`
-  - Direct `.md` files: the file content is used as-is (front matter stripped); no `SKILL.md` lookup needed
-- **Path-based role resolution**: `--role` now accepts file-system paths in addition to role IDs
-  - Absolute and home-relative paths bypass the `~/.prompts/roles/` prefix lookup
-  - Example: `aia --role ~/custom/expert.md my_prompt`
-- **Skills in chat-only mode**: `ChatLoop` now loads and sends configured skills to the AI at session start via `process_skill_context`, even when no pipeline prompt is specified; the AI's acknowledgment is displayed so the user can confirm the skill was applied
-- **`AIA::SkillUtils` module**: New shared utility module (`lib/aia/skill_utils.rb`) consolidating path and skill helpers previously duplicated across four classes
-  - `path_based_id?(id)` — detects `/`, `~/`, `./`, `../` prefixes
-  - `parse_front_matter(path)` — reads and parses YAML front matter from a `.md` file; returns `{}` on any failure
-  - `find_skill_dir(skill_name, base_dir)` — resolves a skill name or path to its directory (or direct `.md` file); enforces symlink/prefix-traversal checks for ID-based lookups
-  - `safe_skill_path(path, dir)` — verifies a resolved path is contained within `dir` using `File::SEPARATOR`-terminated prefix to prevent sibling-directory attacks
-  - `skill_body(content)` — strips YAML front matter from skill file content
-  - Included by `PromptPipeline`, `PromptHandler`, `WebAndFileDirectives`, `CLIParser`, `ConfigValidator`, and `ChatLoop`
-- **`roles` config section**: Top-level `roles.dir` config key (`~/.prompts/roles` default) alongside existing `prompts.roles_prefix`
-- **`parse_search_terms` helper**: New private method on `AIA::Directive` base class available to all directive subclasses; splits argument tokens into `[positive_terms, negative_terms]` arrays (negative prefixes: `-`, `~`, `!`; positive: `+` or bare; all downcased)
+
+- **Skills system** (`lib/aia/skill_utils.rb`, `lib/aia/directives/web_and_file_directives.rb`): Mainline added `SKILL.md`-based skills, `/skill`, `/skills`, `--skill`, `--list-skills`, `--skills-dir`, `--skills-prefix`, path-based skill IDs, and shared `AIA::SkillUtils` helpers.
+- **Path-based role resolution** (`lib/aia/prompt_handler.rb`, `lib/aia/config/cli_parser.rb`, `lib/aia/config/validator.rb`): `--role` and role loading now accept file-system paths in addition to configured role IDs.
+- **Top-level `roles` and `skills` config sections** (`lib/aia/config/defaults.yml`): Added dedicated directory configuration while preserving prompt prefix settings.
+- **Shared search-term parsing** (`lib/aia/directive.rb`): Directive filtering now uses common positive and negative term parsing.
 
 ### Bug Fixes
-- **Direct `.md` skill files silently ignored**: `--skill ./my-skill.md` previously returned `nil` because `find_skill_dir` only checked `Dir.exist?`. Now checks `File.file?` and returns the path directly; `load_skills` and `/skill` read and strip front matter from the file without requiring a `SKILL.md` sub-file
-- **Path-prefix collision in `safe_skill_path`**: A sibling directory named `skills-attack` could bypass the containment check against `skills` because `start_with?(realpath)` matched the shared prefix. Fixed by appending `File::SEPARATOR` to the base path before the `start_with?` comparison
-- **Path-based role IDs incorrectly prefixed**: `ConfigValidator#process_role_configuration` was unconditionally prepending the roles prefix (e.g., `roles/`) to role IDs, corrupting absolute and relative paths like `/custom/role.md` into `roles//custom/role.md`. Now guards with `AIA::SkillUtils.path_based_id?` before applying the prefix
+
+- **Direct skill file resolution**: Skill loading now accepts direct `.md` file paths as well as skill directories.
+- **Skill path-prefix containment**: Mainline added realpath boundary checks to block sibling-directory prefix attacks.
+- **Path-based role prefixing**: Config tailoring no longer prepends the roles prefix to path-based role IDs.
 
 ### Improvements
-- **`/available_models` filtering** now uses `parse_search_terms` for consistent positive/negative term filtering across local (Ollama, LM Studio) and cloud model listings
-- **Standardized warning output**: Replaced `$stderr.puts` with `warn` throughout `prompt_pipeline.rb` for idiomatic Ruby error reporting
-- **Skills CLI options moved to Prompt Options group**: `--skill`, `--skills-dir`, `--skills-prefix`, `--list-skills` now appear under `--help`'s Prompt Options section alongside `--role` and related options, rather than Model Options
 
-### Testing
-- Added `test/aia/skill_utils_test.rb` — 24 tests covering all `AIA::SkillUtils` methods including symlink traversal blocking, sibling-prefix collision, direct `.md` file resolution, and nonexistent path handling
-- Added `test/aia/config/cli_parser_skills_test.rb` — 8 tests covering all skills-related CLI options
-- Added `test/aia/config/skills_config_test.rb` — 8 tests covering skills config defaults and overrides
-- Added `test/aia/directive_search_terms_test.rb` — 10 tests covering all `parse_search_terms` token forms
-- Expanded `test/aia/directives/skill_directive_test.rb` with path-based, direct-file, security (path traversal, symlink), and edge-case coverage (36 tests total)
-- Added `test/aia/prompt_pipeline_skills_test.rb` — pipeline-level skill loading tests including absolute paths, direct `.md` files, warning capture via Mocha stubs, and mixed path+ID loading (6 tests)
-- Added `test/aia/session_test.rb` `ChatLoopTest` entries for `process_skill_context` — noop when no skills configured, sends skill content to processor when configured (2 tests)
-- Eliminated `Dir.chdir` side effects from 3 tests (`skill_directive_test.rb`, `prompt_pipeline_skills_test.rb`, `prompt_handler_role_path_test.rb`) that used it to simulate relative-path resolution; replaced with absolute-path construction
-- Updated 2 pipeline warning tests to use Mocha's `.stubs(:warn).with { }` argument-matcher pattern instead of `capture_io` (which cannot intercept `warn` when `$stderr` is reassigned in Ruby 4.0)
-- Full test suite: 925 runs, 0 failures, 0 errors, 0 skips
+- **Model and skill filtering consistency**: `/llms` and `/skills` use the shared positive/negative search term behavior.
+- **Skills CLI option placement**: Skill-related CLI flags now appear under Prompt Options.
+
+## [2.0.9.alpha] - 2026-03-28
+
+### Improvements (Section 9 — Design Correctness)
+
+- **`MCPConfigNormalizer.filter_servers` eliminated** (`lib/aia/mcp_config_normalizer.rb`, `lib/aia/robot_builder.rb`, `lib/aia/robot_factory.rb`): `filter_servers` duplicated use/skip filtering logic that `MCPDiscovery` already owns, and used a different activation source (`TurnState.active_mcp_servers` vs. `Decisions.mcp_activations`), creating a split-brain risk. Removed `filter_servers` entirely. `RobotBuilder` now passes all configured servers normalized (`Array(config.mcp_servers).map { |s| MCPConfigNormalizer.normalize(s) }`). `RobotFactory.mcp_server_configs` (used by network builders) follows the same pattern. MCPDiscovery is now the single authoritative filter.
+- **`Utility` converted from class to module** (`lib/aia/utility.rb`): `class Utility` with only `class << self` methods is a Ruby anti-pattern. Changed to `module Utility` — semantically identical for callers (`AIA::Utility.mcp_servers?` etc.) but idiomatically correct. Nothing can be accidentally instantiated.
+- **Banner methods returned to `Utility`** (`lib/aia/utility.rb`, `lib/aia/mcp_utility.rb`, `lib/aia/tool_utility.rb`): `banner_mcp`, `mcp_client_labels`, and `banner_tools` were mixed into `MCPUtility`/`ToolUtility` — display concerns in data-query modules. Moved all banner private methods back into `Utility`. `MCPUtility` and `ToolUtility` are now pure query interfaces with no formatting logic.
+- **`MCPDiscovery` takes `decisions` directly** (`lib/aia/mcp_discovery.rb`, `startup_coordinator.rb`, `pipeline_orchestrator.rb`, `special_mode_handler.rb`): `MCPDiscovery` only ever used `rule_router.decisions` — passing the whole `rule_router` was over-coupling. Constructor changed to `MCPDiscovery.new(decisions)`; all three callers updated to pass `@rule_router.decisions`. Dependency is now explicit and narrow.
+- **`history_manager.rb` shim deleted** (`lib/aia/session.rb`): The backward-compat shim (`require_relative 'variable_input_collector'`) had served its purpose. `session.rb` updated to require `variable_input_collector` directly. The Ruby-level `HistoryManager = VariableInputCollector` alias in `variable_input_collector.rb` remains for callers that reference the old constant name.
+
+## [2.0.8.alpha] - 2026-03-28
+
+### Improvements (Section 8 — Backlog Cleanup)
+
+- **Consolidate `server_name` inline patterns** (`fact_asserter.rb`, `config/validator.rb`, `mcp_discovery.rb`): Replaced 5 occurrences of `server[:name] || server['name']` with `Utility.server_name(server)` (or `AIA::Utility.server_name(server)`). `Utility.server_name` already handled Hash symbol/string keys, object `.name` methods, and `to_s` fallback — the inline pattern was a redundant re-implementation. (P3-28 / 8.1)
+- **`MCPUtility` and `ToolUtility` extracted from `Utility`** (`lib/aia/mcp_utility.rb`, `lib/aia/tool_utility.rb`, `lib/aia/utility.rb`): `Utility` was a grab-bag class mixing MCP server query methods, tool query methods, and display/banner concerns. Extracted `MCPUtility` (6 public methods: `mcp_servers?`, `mcp_server_names`, `connected_mcp_servers?`, `failed_mcp_servers`, `effective_mcp_server_names`, `server_name`; 2 private: `mcp_client_labels`, `banner_mcp`) and `ToolUtility` (4 public methods: `tools?`, `total_tool_count`, `user_tools?`, `supports_tools?`; 1 private: `banner_tools`). Both modules are included into `Utility` via `class << self include`. `utility.rb` now holds only display, banner, and model-refresh concerns. (P3-30 / 8.2)
+- **Pin `robot_lab` and `kbs` version constraints** (`aia.gemspec`): Simplified redundant double-constraint notation (`'~> 0.0', '>= 0.0.9'`) to single pessimistic constraints: `robot_lab '~> 0.0.9'` and `kbs '~> 0.2.1'`. Semantically equivalent but cleaner. (P3-32 / 8.3)
+- **Rename `HistoryManager` → `VariableInputCollector`** (`lib/aia/variable_input_collector.rb`, `lib/aia/history_manager.rb`, `lib/aia/input_collector.rb`): `HistoryManager` was misnamed — it only prompts for prompt variable values. New canonical name is `VariableInputCollector`. `history_manager.rb` is now a one-line shim requiring the new file. `HistoryManager = VariableInputCollector` alias preserved for backward compatibility. `lib/aia.rb` updated to require `variable_input_collector`. New test file `test/aia/variable_input_collector_test.rb` mirrors the original tests plus an alias assertion. (P3-33 / 8.4)
+
+## [2.0.7.alpha] - 2026-03-28
+
+### Improvements (Section 7 — MCPDiscovery Decision)
+
+- **`MCPDiscovery` wired into `StartupCoordinator`** (`lib/aia/startup_coordinator.rb`): The startup MCP connection path now routes through `MCPDiscovery#discover` instead of the indirect `MCPConfigNormalizer.filter_servers → TurnState` bridge. `MCPDiscovery` is the canonical authority for which servers are activated at startup — reading `--mcp-use`, `--mcp-skip`, and KBS `mcp_activate` decisions directly. Each discovered server is then normalized by `MCPConfigNormalizer.normalize` before being passed to `MCPConnectionManager`. (P2-20 / 7.1)
+- **`MCPDiscovery` bug fix** (`lib/aia/mcp_discovery.rb`): `config.mcp_use` truthiness check changed from `if config.mcp_use` to `if Array(config.mcp_use).any?`. In Ruby, `[]` is truthy, so an empty `mcp_use` list previously triggered explicit-server filtering and returned zero servers. An empty list now correctly falls through to KBS-activation or all-servers fallback. (7.1)
+- **`MCPDiscovery` now respects `--mcp-skip`** (`lib/aia/mcp_discovery.rb`): Added `apply_skip_filter` that removes servers whose names appear in `config.mcp_skip` after the primary selection (explicit, KBS-activated, or all). Skip is applied regardless of which selection path was taken. (7.1)
+- **Refactored `MCPDiscovery` internals** (`lib/aia/mcp_discovery.rb`): Extracted `select_servers` (selection strategy dispatcher), `apply_skip_filter` (post-selection skip), and `select_by_names` (name-list filter) private helpers. The public `discover` interface is unchanged. (7.1)
+
+## [2.0.6.alpha] - 2026-03-28
+
+### Improvements (Section 6 — Structural Decompositions)
+
+- **`ConfigValidator` early-exit refactor** (`lib/aia/config/validator.rb`): Replaced all `raise AIA::EarlyExit` calls with `return :early_exit`. `tailor()` propagates the signal via `return :early_exit if <step>(config) == :early_exit`. Removed the `EarlyExit` exception class from `lib/aia/errors.rb` and the `rescue AIA::EarlyExit` clause from `lib/aia.rb`. The exception-as-goto anti-pattern is gone. (P2-18 / 6.1)
+- **`ExpertRouter` integration** (`lib/aia/expert_router.rb`): `ExpertRouter` is now instantiated in `ChatLoop` and called as part of the turn pipeline. Verified via `test_expert_router_is_integrated_into_chat_loop`. (P2-19 / 6.2)
+- **`TaskDecomposer` + `TaskExecutor`** (`lib/aia/task_decomposer.rb`, `lib/aia/task_executor.rb`): Extracted from `DelegateHandler`. `TaskDecomposer#decompose` calls the lead robot with a JSON decomposition prompt and returns `[{title:, assignee:}]`. `TaskExecutor#execute` claims, runs, and completes a single TrakFlow step. `DelegateHandler` is now a thin coordinator. (P2-23 / 6.3)
+- **`StartupCoordinator`** (`lib/aia/startup_coordinator.rb`): New class extracting all session startup concerns from `Session`: MCP server connection, tool collection, filter registry initialization, TrakFlow bootstrap, and bus attachment. `StartupCoordinator.new(robot:, rule_router:, ui_presenter:).run(config)` runs all startup tasks and exposes `filters` and `mcp_manager` attributes. (P2-16 / 6.4)
+- **`PipelineOrchestrator`** (`lib/aia/pipeline_orchestrator.rb`): New class extracting per-prompt pipeline processing from `Session`: prompt building (role, stdin, context files), concurrent MCP detection, robot dispatch, result display, metrics, and TrakFlow step tracking. `PipelineOrchestrator.new(...).process(config)` replaces `Session#process_pipeline` and all its private helpers. (P2-16 / 6.4)
+- **`Session` thinned** (`lib/aia/session.rb`): `Session#start` now delegates to `StartupCoordinator#run` and `PipelineOrchestrator#process`. The 12 extracted private methods (`connect_mcp_servers`, `process_pipeline`, `execute_prompt`, `maybe_use_concurrent_mcp`, `build_prompt_text`, `add_context_files`, `display_metrics`, etc.) have been removed. Session is a thin shell sequencing startup → pipeline → chat. (P2-16 / 6.4)
+- **`MCPConfigNormalizer`** (`lib/aia/mcp_config_normalizer.rb`): New class extracting MCP server filtering and normalization from `RobotFactory`. `MCPConfigNormalizer.filter_servers(config)` applies use/skip/KBS lists and returns normalized configs. `MCPConfigNormalizer.normalize(server)` converts flat format to robot_lab's nested transport format. `RobotFactory#mcp_server_configs` and `#normalize_mcp_config` now delegate to it. (P2-17 / 6.5)
+- **`NetworkMemoryManager`** (`lib/aia/network_memory_manager.rb`): New class extracting network shared-memory setup from `RobotFactory`. `NetworkMemoryManager.initialize_memory(network, config)` seeds session metadata. `NetworkMemoryManager.setup_subscriptions(network, config)` wires debug-logging and completion-count subscriptions. `RobotFactory#initialize_network_memory` and `#setup_memory_subscriptions` now delegate to it. (P2-17 / 6.5)
+- **`RobotBuilder`** (`lib/aia/robot_builder.rb`): New class extracting single-robot construction from `RobotFactory`. `RobotBuilder.build(config, namer:)` assembles the system prompt, resolves MCP configs via `MCPConfigNormalizer`, and calls `RobotLab.build`. `RobotFactory#build_single_robot` now delegates to it. (P2-17 / 6.5)
+
+## [2.0.5.alpha] - 2026-03-27
+
+### Improvements (Section 5 — State Machine & Lifecycle)
+
+- **`TurnState#request(mode)` mutual exclusion** (`lib/aia/turn_state.rb`): Added `EXCLUSIVE_MODES` constant and `request(mode, type: nil)` method. Calling `request` clears all other exclusive `force_*` flags before setting the new one, enforcing that only one special mode is active at a time. Added `active_mode` helper returning the currently active mode symbol. Direct `attr_accessor` assignment still works for backward compatibility and test assertions. (P1-13)
+- **`SpawnHandler` lifecycle** (`lib/aia/spawn_handler.rb`): Added `MAX_CACHE_SIZE = 5` constant. When a new specialist is spawned and the cache is full, the oldest entry is evicted (insertion-order LRU via Ruby Hash). Added `cleanup!` method that clears all cached specialists — called on session end to release resources. (P2-22)
+- **`DebateHandler` convergence** (`lib/aia/debate_handler.rb`): Replaced the fragile `"CONVERGED"` string check with semantic similarity scoring using `SimilarityScorer`. Added `MIN_ROUNDS = 2` and `SIMILARITY_THRESHOLD = 0.85`. Convergence is only evaluated after `MIN_ROUNDS` rounds; it triggers when the combined response text from consecutive rounds scores ≥ threshold. One robot mentioning "CONVERGED" incidentally no longer ends the debate prematurely. (P2-21)
+- **`MentionRouter` mention stripping** (`lib/aia/mention_router.rb`): After matching `@mention` tokens to robots, all mention tokens are stripped from the prompt (`gsub(/@\w+\s*/i, '').strip`) before routing to the target robot. The robot now receives only the query, not the routing prefix. (P3-26)
+- **`ModelSwitchHandler#model_exists?` caching** (`lib/aia/model_switch_handler.rb`): Added `@model_exists_cache` instance hash. Each model name is looked up via `RubyLLM.models.find(name)` at most once per handler instance; subsequent calls for the same name return the cached boolean without hitting the provider. (P3-27)
+
+## [2.0.4.alpha] - 2026-03-27
+
+### Improvements (Section 4 — Tool Infrastructure)
+
+- **`ToolLoader` converted to class** (`lib/aia/tool_loader.rb`): `module_function` with a module-level `@tool_cache` was replaced by a class with per-instance `@tool_cache`. Class-level convenience methods delegate to a resettable default instance via `ToolLoader.instance`. `ToolLoader.reset_instance!` (and `AIA.reset!`) discard the singleton for clean test isolation. Two `ToolLoader.new` instances now have independent caches. (P1-12)
+- **`ToolFilterRegistry`** (`lib/aia/tool_filter_registry.rb`): New class with `build_from_config(config, tools, rule_router:)`. Extracts the five identical `if/prep/assign` blocks from `Session#start` into a single, independently testable method. Session now calls one line. (P1-7)
+- **`EmbeddingModelLoader` mixin** (`lib/aia/tool_filter/embedding_model_loader.rb`): New module with `load_embedding_model(label, model_name)`. Included by both `ToolFilter::Zvec` and `ToolFilter::SqliteVec`, removing two identical 3-line embedding-load sequences. (P3-25)
+- **`ToolFilter::SqliteVec` rowid mapping** (`lib/aia/tool_filter/sqlite_vec.rb`): Replaced fragile `@tool_entries[rowid - 1]` positional lookup with `@tool_index` hash (`rowid → entry`). Both `create_database` and `load_persisted` populate the index; `do_filter_with_scores` uses `@tool_index[rowid]`. Lookup is now stable across deletions and reinsertions. (P3-31)
+- **`ToolFilter::TFIDF` vectorizer caching** (`lib/aia/tool_filter/tfidf.rb`): `Classifier::TFIDF.new`, `fit`, and full-corpus `transform` were called on every user turn. Now the vectorizer is fitted and all tool vectors are computed once in `do_prep` and cached as `@tfidf` / `@tool_vectors`. Per-turn cost is reduced to a single `@tfidf.transform(prompt)` call. (P3-24)
+
+## [2.0.3.alpha] - 2026-03-27
+
+### Improvements (Section 3 — Handler Cleanup)
+
+- **`ContentExtractor#extract_content`**: Replaced three identical `extract_reply` private methods in `SpawnHandler`, `DebateHandler`, and `DelegateHandler` with a single call to the shared `ContentExtractor#extract_content`. (P1-9)
+- **`HandlerProtocol` module** (`lib/aia/handler_protocol.rb`): New module defining the `handle(context)` interface. All five turn-level handlers now `include HandlerProtocol` and raise `NotImplementedError` from the base if `handle` is not overridden.
+- **`HandlerContext` struct** (`lib/aia/handler_context.rb`): New value object carrying `robot`, `prompt`, `decisions`, `config`, and `specialist_type` — replaces five incompatible handler signatures with a single unified protocol. All five handlers (`SpawnHandler`, `DebateHandler`, `DelegateHandler`, `MentionRouter`, `ModelSwitchHandler`) migrated to `handle(context)`. All call sites in `SpecialModeHandler` and `ChatLoop` updated. (P1-8)
+- **`Fzf`**: Removed dead code — `tempfile_path` method, `unlink_tempfile` method, and the `ensure` block that called `unlink_tempfile`. `fzf` now passes list items via `stdin_data:` only; no tempfile is created. (P3-29)
+- **Section 3.4** was completed as part of Section 2.5 (`UIPresenter#calculate_cost` already delegates to `CostCalculator`).
+
+## [2.0.2.alpha] - 2026-03-27
+
+### Improvements (Section 2 — Correctness Completions)
+
+- **`DecisionApplier`**: When `build_temp_robot` returns nil, now emits a `warn` and explicitly sets `context.model_overridden = false` before returning. Previously the turn fell through silently with no indication the model switch failed. (C4)
+- **`FactAsserter`**: Changed `config.models.each` → `Array(config.models).each` to prevent `NoMethodError` when `config.models` is nil during early KBS evaluation. (P1-10)
+- **`RuleRouter`**: Changed silent `next unless kb` to emit a structured warning (`[RuleRouter] Warning: knowledge base '#{name}' not found in pipeline — skipping`) when a KB from `KB_ORDER` is absent. Missing KBs no longer cause silent rule failures. (C5)
+- **`TrakFlowBridge`**: `attr_reader :db` moved from `private` to public. The database accessor is now part of the public API.
+- **`TaskCoordinator`**: Replaced `bridge.send(:db)` with `bridge.db`, removing the private-access workaround.
+- **New `AIA::CostCalculator` module** (`lib/aia/cost_calculator.rb`): Extracts the duplicated cost calculation logic that previously lived in `SessionTracker` and `UIPresenter`. Single entry point: `AIA::CostCalculator.calculate(model_id:, input_tokens:, output_tokens:)` → `{ available:, total_cost:, input_cost:, output_cost: }`. (P1-15)
+- **`SessionTracker`**: `compute_cost_for_model` and `compute_cost` now delegate to `CostCalculator`.
+- **`UIPresenter`**: `calculate_cost` now delegates to `CostCalculator`.
+
+## [2.0.1.alpha] - 2026-03-27
+
+### Improvements (Section 1 — Safety Net)
+
+- **`MCPConnectionManager`**: All reads of `@connected_clients`, `@connected_tools`, and `@connected_servers` are now wrapped in `@mutex.synchronize`. Eliminates data races between `connect_one` threads and callers of `inject_into`, `update_config`, `any_tools?`, `connected_server_names`, and `failed_server_names`. (C1)
+- **`AIA.reset!`**: New class method that nils all seven mutable singletons (`@config`, `@client`, `@session_tracker`, `@turn_state`, `@task_coordinator`, `@decisions`, `@rule_router`) for clean test isolation. (C2)
+- **`Decisions#add(:model_decision)`**: Now raises `ArgumentError` when `:model` is nil, preventing silent propagation of invalid model decisions downstream. (C3)
+- **`HistoryManager`**: All three `exit(1)` calls replaced with `raise AIA::Error`. Callers can now rescue or propagate the error; `AIA.run` catches it and exits with a message. (C7)
+- **`ToolFilter::TFIDF`**: Replaced undefined `logger.warn` in the rescue path with `Kernel#warn`, eliminating a `NoMethodError` that would mask the original classifier error. (P1-16)
+
+## [2.0.0.alpha] - 2026-03-26
+
+### Breaking Changes
+- **New execution engine**: AIA is now powered by `robot_lab` and `kbs`. The `RubyLLMAdapter` and the entire `lib/aia/adapter/` layer have been removed.
+- **`AIA.client` is now a `RobotLab::Robot` or `RobotLab::Network`**, built by `AIA::RobotFactory`. Code that references `AIA::RubyLLMAdapter` directly must be updated.
+- **Removed gems**: `ostruct` and `securerandom` are no longer dependencies.
+
+### New Features
+- **`RobotFactory`**: Single entry point for building the AI backend. Supports single robot, parallel multi-model, consensus network, and pipeline network modes.
+- **`RuleRouter` with multi-KB architecture**: RETE-based rule engine (via `kbs` gem) with five specialized knowledge bases — input classification, model selection, MCP/tool routing, quality gates, and post-response learning.
+- **`NetworkBuilder`**: Extracted network construction for pipeline, parallel, and consensus topologies.
+- **Dynamic model switching**: Mid-session model changes via `ModelSwitchHandler`, `ModelAliasRegistry` (fuzzy name matching), and `HistoryTransfer` (conversation continuity across switches).
+- **`@mention` routing**: `MentionRouter` routes prompts to named robots via `@model-name` syntax in chat.
+- **MCP concurrency**: `McpConnectionManager` maintains persistent stdio connections; `McpDiscovery` and `McpGrouper` classify and route servers by capability.
+- **TrakFlow integration**: `TrakFlowBridge` creates plans from prompt pipelines and tracks task state. New `/trak` directives. TrakFlow MCP server config included.
+- **Advanced RobotLab patterns**:
+  - `VerificationNetwork` — two robots answer independently, a reconciler produces a verified result
+  - `DebateHandler` — multi-round debate between robots with convergence detection (max 5 rounds)
+  - `PromptDecomposer` — breaks complex prompts into parallel subtasks
+  - `ExpertRouter` — KBS-driven routing to domain-specialist robots with tailored model and MCP selection
+  - `SpawnHandler` / `DelegateHandler` — dynamic robot spawning and subtask delegation
+- **Built-in tools**: `DelegateToForemanTool` and `TaskBoardTool` as `RubyLLM::Tool` subclasses.
+- **`DynamicRuleBuilder`**: Generates KBS route rules at runtime from discovered local tools and MCP servers, matching domains to activate the appropriate tools per turn.
+- **Semantic tool filtering**: Multiple backends in `lib/aia/tool_filter/` — KBS, LSI, TF-IDF, sqlite-vec, and zvec.
+- **`SessionTracker` and `TurnState`**: Per-session and per-turn state containers for metrics and cost tracking.
+- **`SystemPromptAssembler`**: Extracted system prompt resolution including role loading.
+- **`RobotNamer`**: Deterministic unique robot name generation.
+
+### Improvements
+- `RobotFactory` decomposed into focused collaborators (`NetworkBuilder`, `ToolLoader`, `ToolFilter`, `SystemPromptAssembler`, `RobotNamer`)
+- `RuleRouter` refactored from single-KB to multi-KB registry with typed `Decisions` struct
+- `FactAsserter` and `DecisionApplier` extracted for testability; `FactAsserter` now supports asserting additional fact types
+- `StreamingRunner` extracted from `ChatLoop`
+- New `rules_dsl.rb` provides a user-facing DSL for writing custom routing rules
+- `ChatLoop` refactored AI response handling for cleaner robot tool execution and logging
+- `ChatLoop` improved empty user input handling — empty input exits cleanly (break) rather than looping
+- `Decisions` gains `group_by_mcp_server` — groups tool activations by their originating MCP server
+
+### Dependencies
+- Added: `robot_lab ~> 0.0, >= 0.0.9`, `kbs ~> 0.2, >= 0.2.1`, `trak_flow`, `classifier`, `zvec`, `sqlite-vec`, `informers`
+- Removed: `ruby_llm` adapter layer (still used transitively via `robot_lab`)
+- `Gemfile.lock` added to `.gitignore`
 
 ## [1.0.0] - 2026-02-22
 
@@ -778,7 +992,7 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
 - fixed a problem with a priming prompt in a chat loop
 
 ## [0.9.0] 2025-05-13
-- Adding experimental MCP Client suppot
+- Adding experimental MCP Client support
 - removed the CLI options --erb and --shell but kept them in the config file with a default of true for both
 
 ## [0.8.6] 2025-04-23
@@ -850,7 +1064,7 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
 - Added --image_size and --image_quality (--is --iq)
 
 ## [0.5.15] 2024-03-30
-- Added the ability to accept piped in text to be appeded to the end of the prompt text: curl $URL | aia ad_hoc
+- Added the ability to accept piped in text to be appended to the end of the prompt text: curl $URL | aia ad_hoc
 - Fixed bugs with entering directives as follow-up prompts during a chat session
 
 ## [0.5.14] 2024-03-09
@@ -922,7 +1136,7 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
 
 ## [0.3.20] 2023-12-28
 - added work around to issue with multiple context files going to the `mods` backend
-- added shellwords gem to santize prompt text on the command line
+- added shellwords gem to sanitize prompt text on the command line
 
 ## [0.3.19] 2023-12-26
 - major code refactoring.
@@ -930,7 +1144,7 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
 - usage implemented as a man page. --help will display the man page/
 - added "--dump <yml|yaml|toml>" to send current configuration to STDOUT
 - added "--completion <bash|fish|zsh>" to send a a completion function for the indicated shell to STDOUT
-- added system environment variable (envar) over-rides of default config values uppercase environment variables prefixed with "AIA_" + config item name for example AIA_PROMPTS_DIR and AIA_MODEL.  All config items can be over-ridden by their cooresponding envars.
+- added system environment variable (envar) over-rides of default config values uppercase environment variables prefixed with "AIA_" + config item name for example AIA_PROMPTS_DIR and AIA_MODEL.  All config items can be over-ridden by their corresponding envars.
 - config value hierarchy is:
     1. values from config file  over-rides ...
     2. command line values      over-rides ...
@@ -939,7 +1153,7 @@ aia --chat -m gpt-4o-mini,gpt-3.5-turbo
 
 ## [0.3.0] = 2023-11-23
 
-- 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.
+- Matching version to [prompt_manager](https://github.com/prompt_manager) This version allows for the user of history in the entry of values to prompt keywords.  KW_HISTORY_MAX is set at 5.  Changed CLI interaction to use historical selection and editing of prior keyword values.
 
 ## [0.1.0] - 2023-11-23