kward 0.67.1 → 0.68.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d03a2b137c3ef3a1bc27e44b2629de49a41c70c3044088f9bd0c162cf50e3387
-  data.tar.gz: 241753e7eca9acb6ff94cae50afa7ea43ea2e4c13a8d22eb5031d399ae7fad5a
+  metadata.gz: 73a17b20e90d49d2bd6b3a7379e19e93bf21f44b14da57b572d34dc36068e49d
+  data.tar.gz: f521cd144677b097744b1e97913b47cb322760c526eee68c2b7262d57856c676
 SHA512:
-  metadata.gz: ac0d8465faa573ac9878c4bf5b83327145a7810cbe375b64ce8019531ba00ea3be779a82ed912825de2372ba18917dc56137f67f60161d3234e396b6ec82f3a2
-  data.tar.gz: 3e50a23badb84faf825a75cec5f9d0f4b62cc2bb0c76d643ac8bfb41d99a97c0cbc95268508e4b8a0c2e172249d105f3246b8b0e6a44c81725eae52db71235e6
+  metadata.gz: 24b64b2f6a4ab6d7e3c9ac4d819994b3add061c8ef0d19ac164aed829b9160639ed9dde1e0b3a7ebaf478e8b2bb515ce8d5c13710ab4adb246f9e4929c85214b
+  data.tar.gz: 48ba9b202ac846fb98123edf732f9ec9e58bacfb63ac7e4e58b6e9f4dd4d9e04c5d0d096477344f494f9539a569e261d531ece9fa6d94d65fec41e57223819be

data/CHANGELOG.md

@@ -4,6 +4,26 @@ All notable changes to Kward will be documented in this file.
 
 ## [Unreleased]
 
+## [0.68.0] - 2026-06-14
+
+In this release, most changes are under the hood, as it included massive refactors to have an even more robust way forward.
+
+### Added
+
+- Added Anthropic Claude Pro/Max subscription provider support with OAuth login, static Claude model choices, and Anthropic Messages streaming.
+
+### Changed
+
+- Changed known context windows and reasoning effort choices to use provider/model-specific metadata for Codex, OpenRouter, Copilot, and Anthropic models.
+- Changed the default Anthropic model to Claude Sonnet 4.6 and expanded direct Anthropic model choices to include newer Claude Opus/Sonnet releases.
+- Changed resumed sessions to restore the session's last-used provider, model, and reasoning effort without rewriting default config.
+- Documented the tool contract: schemas define strict generated/returned payloads, while runtime accepts tolerant incoming tool-call input for compatibility.
+- Expanded RDoc coverage past 50% across message compatibility, tool-call normalization, session persistence, session tree helpers, model/client boundaries, config paths, workspace operations, telemetry, RPC, plugins, memory, auth, compaction, search internals, CLI mixins, and prompt interface components.
+
+### Fixed
+
+- Fixed session tree editing and RPC fork text so prompt-template turns use the original visible slash command instead of expanded model content.
+
 ## [0.67.1] - 2026-06-14
 
 ### Fixed

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    kward (0.67.1)
+    kward (0.68.0)
       base64
       nokogiri
       tiktoken_ruby
@@ -66,7 +66,7 @@ CHECKSUMS
   date (3.5.1) sha256=750d06384d7b9c15d562c76291407d89e368dda4d4fff957eb94962d325a0dc0
   drb (2.2.3) sha256=0b00d6fdb50995fe4a45dea13663493c841112e4068656854646f418fda13373
   erb (6.0.4) sha256=38e3803694be357fe2bfe312487c74beaf9fb4e5beb3e22498952fe1645b95d9
-  kward (0.67.1)
+  kward (0.68.0)
   minitest (6.0.6) sha256=153ea36d1d987a62942382b61075745042a2b3123b1cd48f4c3675af9cc7d6f1
   nokogiri (1.19.3-arm64-darwin) sha256=71b9bd424b1b7abc18b05052a1a3cfd3627abdca62be280854cc411791357e42
   pastel (0.8.0) sha256=481da9fb7d2f6e6b1a08faf11fa10363172dc40fd47848f096ae21209f805a75

data/README.md

@@ -2,11 +2,11 @@
 
 Kward is an extendable Ruby CLI coding agent. It can chat with you about a project, inspect and edit files, run confirmed shell commands, search the web, look up public source code, save local sessions, and load trusted Ruby plugins for custom workflows.
 
-It currently supports the OpenAI/ChatGPT Codex backend, OpenRouter, and experimental Copilot provider support.
+It currently supports the OpenAI/ChatGPT Codex backend, Anthropic Claude Pro/Max subscription, OpenRouter, and experimental Copilot provider support.
 
 ## Install
 
-Kward is being prepared for a RubyGems release. Once published, install it with:
+Install Kward from RubyGems:
 
 ```bash
 gem install kward
@@ -54,8 +54,8 @@ exe/kward
 ## What Kward can do
 
 - Keep a multi-turn coding conversation in your terminal.
-- Read, write, and edit workspace files with confirmation before changes.
-- Run shell commands after confirmation.
+- Read, write, and edit workspace files with read-before-write guardrails.
+- Run local shell commands from the workspace.
 - Search the live web and inspect cached public GitHub repositories.
 - Save, resume, clone, compact, and export sessions.
 - Extend the Agent with trusted Ruby plugins for custom commands, footer UI, prompt context, and transcript-event observers.
@@ -69,7 +69,7 @@ Start here:
 - [Getting started](doc/getting-started.md): first run, authentication choices, and basic commands.
 - [Usage](doc/usage.md): interactive chat, slash commands, sessions, tools, images, and Pan mode.
 - [Configuration](doc/configuration.md): config files, providers, models, web search, logging, and color output.
-- [Authentication](doc/authentication.md): OpenAI OAuth, OpenRouter API keys, and Copilot/GitHub setup.
+- [Authentication](doc/authentication.md): OpenAI OAuth, Anthropic OAuth, OpenRouter API keys, and Copilot/GitHub setup.
 - [Troubleshooting](doc/troubleshooting.md): environment-specific install and runtime issues.
 
 Feature guides:

data/doc/authentication.md

@@ -5,6 +5,7 @@ Kward needs credentials for a model provider before it can answer prompts. The e
 Kward supports:
 
 - OpenAI/ChatGPT OAuth for the Codex backend.
+- Anthropic OAuth for Claude Pro/Max subscription support.
 - OpenRouter API keys.
 - GitHub OAuth or `COPILOT_GITHUB_TOKEN` for experimental Copilot provider support.
 
@@ -24,6 +25,7 @@ From your shell, you can also run:
 
 ```bash
 kward login              # OpenAI/ChatGPT OAuth
+kward login anthropic    # Anthropic Claude Pro/Max OAuth
 kward login openrouter   # save an OpenRouter API key
 kward login github       # GitHub OAuth for experimental Copilot support
 ```
@@ -58,6 +60,26 @@ OpenAI OAuth requires an OAuth client ID in `~/.kward/config.json`:
 
 If it is missing, Kward tells you which config file to update.
 
+## Anthropic OAuth
+
+Anthropic OAuth uses your Claude Pro/Max subscription and sends requests to the Anthropic Messages API with Claude Code-compatible subscription headers. To start the browser login from your shell:
+
+```bash
+kward login anthropic
+```
+
+In an interactive session, run `/login` and choose Anthropic.
+
+Tokens are saved to:
+
+```text
+~/.kward/anthropic_auth.json
+```
+
+The auth file is written with file mode `0600`. Kward refreshes the access token when the saved refresh token is available.
+
+Important: Anthropic subscription access follows the same direct OAuth approach Pi uses for Claude Pro/Max. Subscription provider behavior may change upstream.
+
 ## OpenRouter API key
 
 OpenRouter uses an API key rather than OAuth. To save it from your shell:
@@ -97,9 +119,10 @@ Important: Kward's Copilot provider follows Pi Agent's direct HTTPS approach. It
 Credential priority is provider-aware:
 
 - OpenAI OAuth is used by default after login, even when `OPENROUTER_API_KEY` or `openrouter_api_key` is also present.
+- Anthropic OAuth is used when `provider` or `KWARD_PROVIDER` selects `anthropic` or `claude`.
 - `OPENAI_ACCESS_TOKEN` can be used as an OpenAI environment fallback.
 - `OPENROUTER_API_KEY` is a fallback only when no OpenAI OAuth/access token exists.
 - `COPILOT_GITHUB_TOKEN` can be used as a Copilot environment fallback.
-- If `provider` in config or `KWARD_PROVIDER` in the environment is set to `codex`, `openrouter`, or `copilot`, Kward uses that provider and does not fall through to another provider.
+- If `provider` in config or `KWARD_PROVIDER` in the environment is set to `codex`, `anthropic`, `openrouter`, or `copilot`, Kward uses that provider and does not fall through to another provider.
 
 See [Configuration](configuration.md) for model and provider settings.

data/doc/configuration.md

@@ -28,6 +28,7 @@ By default, Kward stores user data under `~/.kward`:
 ```text
 ~/.kward/config.json
 ~/.kward/auth.json
+~/.kward/anthropic_auth.json
 ~/.kward/github_auth.json
 ~/.kward/sessions/
 ~/.kward/memory/
@@ -50,6 +51,7 @@ Set `provider` to choose the active backend:
 Supported values are:
 
 - `codex` for the OpenAI/ChatGPT Codex backend.
+- `anthropic` for Anthropic Claude Pro/Max subscription support.
 - `openrouter` for OpenRouter.
 - `copilot` for experimental Copilot provider support.
 
@@ -60,21 +62,24 @@ Model settings:
   "model": "gpt-5.5",
   "openai_model": "gpt-5.5",
   "openrouter_model": "openai/gpt-5.5",
+  "anthropic_model": "claude-sonnet-4-5",
   "copilot_model": "gpt-5-mini",
   "reasoning_effort": "medium",
   "openai_reasoning_effort": "medium",
   "openrouter_reasoning_effort": "medium",
+  "anthropic_reasoning_effort": "medium",
   "copilot_reasoning_effort": "medium",
   "thinking_level": "medium"
 }
 ```
 
-`model` is a generic setting for the active provider. Provider-specific values such as `openai_model`, `openrouter_model`, and `copilot_model` take precedence for their provider. `reasoning_effort` and `thinking_level` are generic reasoning settings. `openai_reasoning_effort`, `openrouter_reasoning_effort`, and `copilot_reasoning_effort` are provider-specific forms.
+`model` is a generic setting for the active provider. Provider-specific values such as `openai_model`, `anthropic_model`, `openrouter_model`, and `copilot_model` take precedence for their provider. `reasoning_effort` and `thinking_level` are generic reasoning settings. `openai_reasoning_effort`, `anthropic_reasoning_effort`, `openrouter_reasoning_effort`, and `copilot_reasoning_effort` are provider-specific forms.
 
 Defaults:
 
 - OpenAI/Codex: `gpt-5.5`
 - OpenRouter: `openai/gpt-5.5`
+- Anthropic: `claude-sonnet-4-5`
 - Copilot: `gpt-5-mini`
 - Reasoning effort: `medium`
 
@@ -91,6 +96,8 @@ Provider and model:
 - `OPENAI_REASONING_EFFORT`
 - `OPENROUTER_MODEL`
 - `OPENROUTER_REASONING_EFFORT`
+- `ANTHROPIC_MODEL`
+- `ANTHROPIC_REASONING_EFFORT`
 - `COPILOT_MODEL`
 - `COPILOT_REASONING_EFFORT`
 
@@ -122,7 +129,7 @@ Credential settings can also live in config:
 }
 ```
 
-Use environment variables for temporary or local-only secrets when possible. If both OpenAI and OpenRouter credentials are available, OpenAI OAuth is used by default unless `provider` or `KWARD_PROVIDER` selects another backend.
+Use environment variables for temporary or local-only secrets when possible. If multiple credentials are available, OpenAI OAuth is used by default unless `provider` or `KWARD_PROVIDER` selects another backend such as `anthropic`, `openrouter`, or `copilot`.
 
 ## Overlay settings
 

data/doc/extensibility.md

@@ -23,7 +23,7 @@ Plugins are different: user plugins are loaded only from `~/.kward/plugins`, reg
 The optional starter pack installs a useful base `AGENTS.md` and prompt templates. You can install it with:
 
 ```bash
-kward --install-starter-pack
+kward init
 ```
 
 ## Agent instructions

data/doc/getting-started.md

@@ -12,7 +12,7 @@ This page gets you to a first working chat. For day-to-day features after that,
 
 ## Install
 
-Kward is being prepared for a RubyGems release. Once published:
+Install Kward from RubyGems:
 
 ```bash
 gem install kward
@@ -21,16 +21,16 @@ gem install kward
 Optionally install the starter pack:
 
 ```bash
-kward --install-starter-pack
+kward init
 ```
 
 The starter pack adds useful default prompts and a base `AGENTS.md` to your config directory. It is helpful for a first setup, but safe to skip if you want to write your own instructions. Existing files are not overwritten.
 
-Until the gem is published, run Kward from a repository checkout:
+If you are working from a repository checkout:
 
 ```bash
 bundle install
-ruby lib/main.rb --install-starter-pack   # optional
+ruby lib/main.rb init   # optional
 ```
 
 ## Start Kward and sign in
@@ -108,8 +108,6 @@ Kward saves interactive sessions under `~/.kward/sessions/`.
 ## Safety basics
 
 - Kward must read an existing file in the current conversation before it can edit or overwrite it.
-- File writes and edits ask for confirmation first.
-- Shell commands ask for confirmation before running.
 - Tool reads are bounded so large files are not accidentally loaded into context.
 
 ## Run tests

data/doc/plugins.md

@@ -24,8 +24,6 @@ Kward loads top-level Ruby files from:
 
 Plugins are intentionally **not** loaded from the current workspace, from a project repository, or from a custom `KWARD_CONFIG_PATH` directory. This keeps plugin loading tied to the local user account rather than to whatever project Kward is currently inspecting.
 
-If a legacy plugin directory exists beside a custom config path, Kward warns and ignores it.
-
 ## A first plugin
 
 Create the plugin directory:

data/doc/releasing.md

@@ -1,6 +1,6 @@
 # Releasing Kward
 
-Release steps that can be completed before publishing:
+Release steps before publishing:
 
 1. Update `CHANGELOG.md` for the version.
 2. Update `Kward::VERSION` in `lib/kward/version.rb`.
@@ -26,11 +26,10 @@ Release steps that can be completed before publishing:
 6. Inspect the packaged files and confirm no local config, sessions, logs, or secrets are included.
 7. Install the built gem locally and smoke test the `kward` executable.
 
-RubyGems setup before the first public release:
+Publish the built gem from the release checkout:
 
-1. Create or sign in to a RubyGems.org account.
-2. Enable multi-factor authentication for the account.
-3. Confirm the `kward` gem name is available.
-4. Add final homepage, source code, changelog, documentation, and bug tracker metadata to `kward.gemspec` once the public repository URLs are final.
-5. Prefer RubyGems trusted publishing for automated releases so long-lived API keys do not need to be stored in CI secrets.
-6. Push the built gem or publish through the trusted publishing workflow.
+```bash
+gem push kward-VERSION.gem
+```
+
+RubyGems MFA is required for publishing. Prefer RubyGems trusted publishing for automated releases if CI publishing is added later, so long-lived API keys do not need to be stored in CI secrets.

data/doc/rpc.md

@@ -59,7 +59,7 @@ Detailed capability fields include:
 - `models`: model/reasoning RPC methods, explicit OpenRouter catalog listing, exposed model fields, and no scoped model support.
 - `runtime`: supported state/stats methods with message-count stats and OpenAI/Codex context usage. Cumulative token and cost stats are not computed.
 - `runtimeSettings`: live `runtime/updateSetting` support for `defaultModel` and `defaultThinkingLevel`, plus `runtime/reload`.
-- `auth`: Tauren auth provider format, OpenAI OAuth, OpenRouter API-key login, and provider logout for stored credentials.
+- `auth`: Tauren auth provider format, OpenAI and Anthropic OAuth, OpenRouter API-key login, and provider logout for stored credentials.
 - `memory`: opt-in structured memory support, interactive prompt injection only, JSON/JSONL local storage, and dedicated `memory/*` methods.
 - `commands`: supported `commands/list` capability for prompt, skill, and plugin command sources, plus plugin execution through `commands/run` or plugin slash turns.
 - `startupResources`: supported startup resource listing for context, skills, prompts, and plugins.
@@ -589,11 +589,11 @@ Updates config, including secret values, and returns a redacted config object. T
 
 ### `auth/status`
 
-Returns whether OpenAI OAuth, OpenAI access token env, and OpenRouter API key env/config are available.
+Returns whether OpenAI OAuth, Anthropic OAuth, OpenAI access token env, and OpenRouter API key env/config are available.
 
 ### `auth/providers`
 
-Returns Tauren-compatible provider cards for OpenAI OAuth and OpenRouter API-key auth. Provider cards report whether credentials are configured, whether they came from stored config or environment variables, and whether stored credentials can be removed.
+Returns Tauren-compatible provider cards for OpenAI OAuth, Anthropic OAuth, OpenRouter API-key auth, and GitHub/Copilot status. Provider cards report whether credentials are configured, whether they came from stored config or environment variables, and whether stored credentials can be removed.
 
 ### `auth/loginWithApiKey`
 
@@ -608,7 +608,7 @@ Stores the API key with `0600` file permissions, refreshes client config, and re
 
 Params:
 
-- `providerId`: `openai` or `openrouter`.
+- `providerId`: `openai`, `anthropic`, or `openrouter`.
 
 Removes stored credentials only. Environment variables remain active and are still reported by `auth/providers`.
 
@@ -616,10 +616,10 @@ Removes stored credentials only. Environment variables remain active and are sti
 
 Params:
 
-- `providerId`: currently `openai`.
+- `providerId`: currently `openai` or `anthropic`.
 - `timeoutSeconds`: optional callback wait timeout.
 
-Provider-scoped wrapper around the OpenAI OAuth flow. The result includes `providerId`, `loginId`, `authorizationUrl`, `redirectUri`, and `status`.
+Provider-scoped wrapper around the OpenAI or Anthropic OAuth flow. The result includes `providerId`, `loginId`, `authorizationUrl`, `redirectUri`, and `status`.
 
 ### `auth/startOpenAILogin`
 

data/doc/usage.md

@@ -82,7 +82,7 @@ Kward can use these tools during a turn:
 
 - `list_directory` and `read_file` to inspect the workspace.
 - `write_file` and `edit_file` to create or change files.
-- `run_shell_command` to run confirmed local commands.
+- `run_shell_command` to run local commands from the workspace.
 - `web_search` to search the live web.
 - `code_search` to find packages, clone public GitHub repositories into cache, and read bounded source snippets.
 - `ask_user_question` to ask structured clarification questions.
@@ -90,8 +90,11 @@ Kward can use these tools during a turn:
 Safety rules:
 
 - Existing files must be read in the current conversation before Kward can write or edit them.
-- Every write, edit, and shell command asks for confirmation first.
 - Text file reads and edits are capped at 256 KiB per file.
+- Tool schemas are the official contract for generated tool calls and returned tool payloads.
+- At runtime, Kward accepts tolerant incoming tool-call input for compatibility: extra fields are ignored, and existing legacy-compatible input shapes remain supported.
+- Required fields and invalid required values still return explicit tool errors.
+- Tool output payloads are kept schema-clean so future model calls and restored transcripts do not depend on accidental extra fields.
 - When successful tool results include unified diffs, the composer status shows live session totals such as `+700|-572`.
 
 ## Slash commands

data/doc/web-search.md

@@ -15,7 +15,7 @@ The `web_search` tool is advertised by default so the agent can use current sour
 1. Exa API when `EXA_API_KEY` is configured, otherwise keyless Exa MCP (`https://mcp.exa.ai/mcp`)
 2. Perplexity API when configured and `allow_model_providers` is true
 3. Gemini API with Google Search grounding when configured and `allow_model_providers` is true
-4. Legacy DuckDuckGo HTML search, then bundled public SearXNG instances
+4. DuckDuckGo HTML search, then bundled public SearXNG instances
 
 Queries are sent over the network to the selected provider. API keys are never bundled with Kward; configure your own keys only if you want higher limits or alternate providers. Set `web_search.enabled` to `false` to hide the tool. Direct `provider: perplexity` or `provider: gemini` requests still use those providers when keys are configured.
 
@@ -23,6 +23,6 @@ Supported arguments:
 
 - `queries`: one to four search strings
 - `max_results`: results per query, default 5, capped at 20
-- `provider`: optional `auto`, `exa`, `perplexity`, `gemini`, `legacy`, or `duckduckgo`
+- `provider`: optional `auto`, `exa`, `perplexity`, `gemini`, or `duckduckgo`
 - `recency_filter`: optional `day`, `week`, `month`, or `year`
 - `domain_filter`: optional list of included domains, or excluded domains prefixed with `-`

data/kward.gemspec

@@ -13,6 +13,10 @@ Gem::Specification.new do |spec|
   spec.required_ruby_version = ">= 3.2"
 
   spec.metadata["rubygems_mfa_required"] = "true"
+  spec.metadata["source_code_uri"] = "https://github.com/kaiwood/kward"
+  spec.metadata["changelog_uri"] = "https://github.com/kaiwood/kward/blob/main/CHANGELOG.md"
+  spec.metadata["documentation_uri"] = "https://github.com/kaiwood/kward#readme"
+  spec.metadata["bug_tracker_uri"] = "https://github.com/kaiwood/kward/issues"
 
   spec.files = Dir.chdir(__dir__) do
     `git ls-files -z`.split("\x0").reject do |file|

data/lib/kward/agent.rb

@@ -8,9 +8,21 @@ require_relative "steering"
 require_relative "telemetry/logger"
 require_relative "tools/registry"
 
+# Namespace for the Kward CLI agent runtime.
 module Kward
   # Runs model turns, handles context compaction, dispatches tool calls, and
   # streams high-level events back to CLI and RPC callers.
+  #
+  # `Agent` is the main turn orchestrator. It should know what a turn means:
+  # append the user's input, call the model, persist assistant/tool messages,
+  # retry once after recoverable context overflow, apply in-flight steering, and
+  # emit frontend-neutral `Events::*` objects. It should not know terminal or RPC
+  # rendering details; callers translate events into their own UI protocol.
+  #
+  # Tool implementations own local side effects. `Client` owns provider HTTP
+  # details. `Conversation` owns transcript state. Keep future changes in the
+  # lowest layer that owns the behavior, and use `Agent` only for cross-step turn
+  # coordination.
   class Agent
     def initialize(client:, tool_registry: ToolRegistry.new, conversation: Conversation.new, telemetry_logger: TelemetryLogger.new)
       @client = client
@@ -67,6 +79,7 @@ module Kward
           overflow_retried = true
           next
         end
+        update_conversation_runtime(message)
         yield Events::AssistantMessage.new(message: message) if block_given?
         @conversation.append_assistant(message)
         steered_after_message = append_steering_events(steering_state)
@@ -207,11 +220,25 @@ module Kward
           on_assistant_delta: assistant_delta,
           on_retry: retry_callback,
           cancellation: cancellation,
-          steering: steering
+          steering: steering,
+          provider: @conversation.provider,
+          model: @conversation.model,
+          reasoning: @conversation.reasoning_effort
         }
       )
     end
 
+    def update_conversation_runtime(message)
+      return unless message.is_a?(Hash)
+
+      provider = message["provider"] || message[:provider]
+      model = message["model"] || message[:model]
+      return if provider.to_s.empty? || model.to_s.empty?
+
+      @conversation.update_runtime_context!(provider: provider, model: model, reasoning_effort: @conversation.reasoning_effort)
+      @conversation.persist_runtime_context!
+    end
+
     def safe_answer(content)
       text = content.to_s
       return text unless claims_file_edit?(text)
@@ -222,7 +249,7 @@ module Kward
     end
 
     def claims_file_edit?(text)
-      text.match?(/\b(I|I've|I have)\s+(changed|updated|modified|edited|created|deleted|wrote)\b/i)
+      text.match?(/\b(?:I|I've|I have)\s+(?:changed|updated|modified|edited|created|deleted|wrote)\s+(?:the\s+)?(?:file|files|[\w.\/-]+\.[\w-]+)\b/i)
     end
 
     def last_file_change_succeeded?

data/lib/kward/ansi.rb

@@ -1,4 +1,6 @@
+# Namespace for the Kward CLI agent runtime.
 module Kward
+  # ANSI color and terminal capability helpers.
   module ANSI
     ESCAPE_PATTERN = /\e\[[0-9;?]*[ -\/]*[@-~]/.freeze
     SGR_PATTERN = /\e\[[0-9;:]*m/.freeze
@@ -125,6 +127,7 @@ module Kward
       rendered.join("\n") + (string.end_with?("\n") ? "\n" : "")
     end
 
+    # String wrapper that strips ANSI escape sequences while preserving visible text operations.
     class MarkdownStream
       def initialize(enabled: ANSI.enabled?)
         @enabled = enabled