threadwell 0.0.0 → 0.0.2

package/docs/settings.md

@@ -0,0 +1,378 @@
+# Settings
+
+Threadwell uses JSON settings files with project settings overriding global settings.
+
+| Location | Scope |
+|----------|-------|
+| `~/.threadwell/agent/settings.json` | Global (all projects) |
+| `.threadwell/settings.json` | Project (current directory, current compatibility path) |
+
+Threadwell-owned runtime data lives under `.threadwell/`. The intended path policy is:
+
+- `.threadwell/settings.json` becomes the primary project settings path.
+- `.threadwell/settings.json` remains a compatibility fallback and must not be removed automatically.
+- `.threadwell/continuity/` becomes the primary native continuity runtime path.
+- `.threadwell/continuity/` remains a compatibility fallback for existing projects.
+- `.threadwell/memory.sqlite`, `.threadwell/artifacts/`, and `.threadwell/features/` remain runtime memory/spec data.
+
+Project settings are resolved relative to the directory where Threadwell is launched. Threadwell now reads `.threadwell/settings.json` first and falls back to `.threadwell/settings.json` when the Threadwell settings file is absent.
+
+Edit directly or use `/settings` for common options.
+
+## All Settings
+
+### Model & Thinking
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `defaultProvider` | string | - | Default provider (e.g., `"anthropic"`, `"openai"`) |
+| `defaultModel` | string | - | Default model ID |
+| `defaultThinkingLevel` | string | - | `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"` |
+| `hideThinkingBlock` | boolean | `false` | Hide thinking blocks in output |
+| `thinkingBudgets` | object | - | Custom token budgets per thinking level |
+
+#### thinkingBudgets
+
+```json
+{
+  "thinkingBudgets": {
+    "minimal": 1024,
+    "low": 4096,
+    "medium": 10240,
+    "high": 32768
+  }
+}
+```
+
+### UI & Display
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `theme` | string | `"dark"` | Theme name (`"dark"`, `"light"`, or custom) |
+| `quietStartup` | boolean | `false` | Hide startup header |
+| `collapseChangelog` | boolean | `false` | Show condensed changelog after updates |
+| `enableInstallTelemetry` | boolean | `true` | Send an anonymous install/update version ping after first install or changelog-detected updates. This does not control update checks |
+| `doubleEscapeAction` | string | `"tree"` | Action for double-escape: `"tree"`, `"fork"`, or `"none"` |
+| `treeFilterMode` | string | `"default"` | Default filter for `/tree`: `"default"`, `"no-tools"`, `"user-only"`, `"labeled-only"`, `"all"` |
+| `editorPaddingX` | number | `0` | Horizontal padding for input editor (0-3) |
+| `autocompleteMaxVisible` | number | `5` | Max visible items in autocomplete dropdown (3-20) |
+| `showHardwareCursor` | boolean | `false` | Show terminal cursor |
+
+### Telemetry and update checks
+
+`enableInstallTelemetry` only controls the anonymous install/update ping to `https://threadwell.local/api/report-install`. Opting out of telemetry does not disable update checks; Threadwell can still fetch `https://threadwell.local/api/latest-version` to look for the latest version.
+
+Set `THREADWELL_SKIP_VERSION_CHECK=1` to disable the Threadwell version update check. Use `--offline` or `THREADWELL_OFFLINE=1` to disable all startup network operations described here, including update checks, package update checks, and install/update telemetry.
+
+### Warnings
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `warnings.anthropicExtraUsage` | boolean | `true` | Show a warning when Anthropic subscription auth may use paid extra usage |
+
+```json
+{
+  "warnings": {
+    "anthropicExtraUsage": false
+  }
+}
+```
+
+### Compaction
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `compaction.enabled` | boolean | `true` | Enable auto-compaction |
+| `compaction.reserveTokens` | number | `16384` | Tokens reserved for LLM response |
+| `compaction.keepRecentTokens` | number | `20000` | Recent tokens to keep (not summarized) |
+
+```json
+{
+  "compaction": {
+    "enabled": true,
+    "reserveTokens": 16384,
+    "keepRecentTokens": 20000
+  }
+}
+```
+
+### Continuity
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `continuity` | boolean | `true` | Enable native project-local continuity re-entry and project awareness |
+
+By default, Threadwell stores operational continuity state under `.threadwell/continuity/` for the current project when continuity commands or intents are used, detects continuity intent in normal user messages, and injects bounded project continuity through the native model-call context provider before model calls. This is separate from session history and is intended for resumable long-running work.
+
+Threadwell reads `.threadwell/continuity/` as a compatibility fallback when `.threadwell/continuity/` does not exist.
+
+Native continuity recognizes messages such as "agrega al plan...", "planifica continuidad", "continúa con el plan", and "finaliza continuidad" without requiring external skills. It writes:
+
+- `.threadwell/continuity/state.json` - structured continuity state
+- `.threadwell/continuity/context.md` - bounded re-entry context
+- `.threadwell/continuity/plan.md` - plan updates captured from user intent
+- `.threadwell/continuity/queue.md` - native continuity queue
+- `.threadwell/continuity/decision-log.md` - decision log
+- `.threadwell/continuity/next-action.md` - next action
+
+The structured state tracks the current task, blockers, open questions, modified files, validation timestamp, handoff summary, queue, recent decisions, and bounded checkpoints when available.
+
+```json
+{
+  "continuity": false
+}
+```
+
+### Threadwell Memory
+
+Threadwell Memory is the planned native memory layer that combines searchable event history, bounded memory injection, `CONTEXT.md` semantic project language, and ADR suggestions. It is separate from native continuity: continuity tracks what is active now, while memory tracks searchable history and durable context.
+
+Planned settings shape:
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `memory.enabled` | boolean | `false` during rollout | Enable local Threadwell memory storage and retrieval |
+| `memory.inject` | boolean | `false` during rollout | Inject bounded relevant memory before model calls |
+| `memory.semanticContext` | boolean | `true` | Use accepted `CONTEXT.md` project terms when relevant |
+| `memory.adrSuggestions` | boolean | `true` | Suggest ADR candidates for durable decisions |
+| `memory.candidateReview` | boolean | `true` | Require review for low-confidence context/ADR candidates |
+| `memory.hud` | boolean | `false` | Show optional memory HUD in the TUI |
+| `memory.retentionDays` | number | `90` | Retain normal memory events for this many days |
+| `memory.maxDbMb` | number | `256` | Preferred maximum memory database size before compaction |
+| `memory.indexToolOutputs` | string | `"summaries"` | Store `"none"`, `"summaries"`, or `"full"` tool output content |
+| `memory.artifactLargeOutputs` | boolean | `true` | Store large outputs as artifacts/content refs instead of prompt text |
+| `memory.aggressiveRouting` | boolean | `false` | Opt-in hard routing/blocking for context-heavy commands |
+
+Recommended default configuration:
+
+```json
+{
+  "memory": {
+    "enabled": true,
+    "inject": true,
+    "semanticContext": true,
+    "adrSuggestions": true,
+    "candidateReview": true,
+    "hud": false,
+    "retentionDays": 90,
+    "maxDbMb": 256,
+    "indexToolOutputs": "summaries",
+    "artifactLargeOutputs": true,
+    "aggressiveRouting": false
+  }
+}
+```
+
+Use this to disable memory while leaving native continuity enabled:
+
+```json
+{
+  "memory": {
+    "enabled": false
+  }
+}
+```
+
+Use this to keep event capture but disable prompt injection:
+
+```json
+{
+  "memory": {
+    "enabled": true,
+    "inject": false
+  }
+}
+```
+
+### Branch Summary
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `branchSummary.reserveTokens` | number | `16384` | Tokens reserved for branch summarization |
+| `branchSummary.skipPrompt` | boolean | `false` | Skip "Summarize branch?" prompt on `/tree` navigation (defaults to no summary) |
+
+### Retry
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `retry.enabled` | boolean | `true` | Enable automatic agent-level retry on transient errors |
+| `retry.maxRetries` | number | `3` | Maximum agent-level retry attempts |
+| `retry.baseDelayMs` | number | `2000` | Base delay for agent-level exponential backoff (2s, 4s, 8s) |
+| `retry.provider.timeoutMs` | number | SDK default | Provider/SDK request timeout in milliseconds |
+| `retry.provider.maxRetries` | number | SDK default | Provider/SDK retry attempts |
+| `retry.provider.maxRetryDelayMs` | number | `60000` | Max server-requested delay before failing (60s) |
+
+When a provider requests a retry delay longer than `retry.provider.maxRetryDelayMs` (e.g., Google's "quota will reset after 5h"), the request fails immediately with an informative error instead of waiting silently. Set to `0` to disable the cap.
+
+```json
+{
+  "retry": {
+    "enabled": true,
+    "maxRetries": 3,
+    "baseDelayMs": 2000,
+    "provider": {
+      "timeoutMs": 3600000,
+      "maxRetries": 0,
+      "maxRetryDelayMs": 60000
+    }
+  }
+}
+```
+
+### Message Delivery
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `steeringMode` | string | `"one-at-a-time"` | How steering messages are sent: `"all"` or `"one-at-a-time"` |
+| `followUpMode` | string | `"one-at-a-time"` | How follow-up messages are sent: `"all"` or `"one-at-a-time"` |
+| `transport` | string | `"sse"` | Preferred transport for providers that support multiple transports: `"sse"`, `"websocket"`, or `"auto"` |
+
+### Terminal & Images
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `terminal.showImages` | boolean | `true` | Show images in terminal (if supported) |
+| `terminal.imageWidthCells` | number | `60` | Preferred inline image width in terminal cells |
+| `terminal.clearOnShrink` | boolean | `false` | Clear empty rows when content shrinks (can cause flicker) |
+| `images.autoResize` | boolean | `true` | Resize images to 2000x2000 max |
+| `images.blockImages` | boolean | `false` | Block all images from being sent to LLM |
+
+### Shell
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `shellPath` | string | - | Custom shell path (e.g., for Cygwin on Windows) |
+| `shellCommandPrefix` | string | - | Prefix for every bash command (e.g., `"shopt -s expand_aliases"`) |
+| `npmCommand` | string[] | - | Command argv used for npm package lookup/install operations (e.g., `["mise", "exec", "node@20", "--", "npm"]`) |
+
+```json
+{
+  "npmCommand": ["mise", "exec", "node@20", "--", "npm"]
+}
+```
+
+`npmCommand` is used for all npm package-manager operations, including installs, uninstalls, and dependency installs inside git packages. Use argv-style entries exactly as the process should be launched. When `npmCommand` is configured, git package dependency installs use plain `install` to avoid npm-specific flags in wrappers or alternate package managers.
+
+Normally the package manager's global modules location is queried using `root -g`. As a special case, if the first element of `npmCommand` is `"bun"`, the modules location will instead be queried with `pm bin -g`.
+
+### Sessions
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `sessionDir` | string | - | Directory where session files are stored. Accepts absolute or relative paths, plus `~`. |
+
+```json
+{ "sessionDir": " .threadwell/sessions" }
+```
+
+When multiple sources specify a session directory, precedence is `--session-dir`, `THREADWELL_CODING_AGENT_SESSION_DIR`, then `sessionDir` in settings.json.
+
+### Model Cycling
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `enabledModels` | string[] | - | Model patterns for Ctrl+P cycling (same format as `--models` CLI flag) |
+
+```json
+{
+  "enabledModels": ["claude-*", "gpt-4o", "gemini-2*"]
+}
+```
+
+### Markdown
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `markdown.codeBlockIndent` | string | `"  "` | Indentation for code blocks |
+
+### Resources
+
+These settings define where to load extensions, skills, prompts, and themes from.
+
+Paths in `~/.threadwell/agent/settings.json` resolve relative to `~/.threadwell/agent`. Paths in `.threadwell/settings.json` resolve relative to `.threadwell`; `.threadwell/settings.json` is still read as a compatibility fallback when `.threadwell/settings.json` is absent. Absolute paths and `~` are supported.
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `packages` | array | `[]` | npm/git packages to load resources from |
+| `extensions` | string[] | `[]` | Local extension file paths or directories |
+| `skills` | string[] | `[]` | Local skill file paths or directories |
+| `skillsEnabled` | boolean | `true` | Load and inject installed skills |
+| `prompts` | string[] | `[]` | Local prompt template paths or directories |
+| `themes` | string[] | `[]` | Local theme file paths or directories |
+| `enableSkillCommands` | boolean | `true` | Register loaded skills as `/skill:name` commands |
+
+Set `skillsEnabled` to `false` to disable skills for this Threadwell configuration without deleting or moving skill files. Arrays support glob patterns and exclusions. Use `!pattern` to exclude. Use `+path` to force-include an exact path and `-path` to force-exclude an exact path.
+
+#### packages
+
+String form loads all resources from a package:
+
+```json
+{
+  "packages": ["threadwell-skills", "@org/my-extension"]
+}
+```
+
+Object form filters which resources to load:
+
+```json
+{
+  "packages": [
+    {
+      "source": "threadwell-skills",
+      "skills": ["brave-search", "transcribe"],
+      "extensions": []
+    }
+  ]
+}
+```
+
+See [packages.md](packages.md) for package management details.
+
+## Example
+
+```json
+{
+  "defaultProvider": "anthropic",
+  "defaultModel": "claude-sonnet-4-20250514",
+  "defaultThinkingLevel": "medium",
+  "theme": "dark",
+  "compaction": {
+    "enabled": true,
+    "reserveTokens": 16384,
+    "keepRecentTokens": 20000
+  },
+  "retry": {
+    "enabled": true,
+    "maxRetries": 3
+  },
+  "enabledModels": ["claude-*", "gpt-4o"],
+  "warnings": {
+    "anthropicExtraUsage": true
+  },
+  "packages": ["threadwell-skills"]
+}
+```
+
+## Project Overrides
+
+Project settings (`.threadwell/settings.json`, or `.threadwell/settings.json` fallback) override global settings. Nested objects are merged:
+
+```json
+// ~/.threadwell/agent/settings.json (global)
+{
+  "theme": "dark",
+  "compaction": { "enabled": true, "reserveTokens": 16384 }
+}
+
+// .threadwell/settings.json (project)
+{
+  "compaction": { "reserveTokens": 8192 }
+}
+
+// Result
+{
+  "theme": "dark",
+  "compaction": { "enabled": true, "reserveTokens": 8192 }
+}
+```

package/docs/shell-aliases.md

@@ -0,0 +1,13 @@
+# Shell Aliases
+
+Threadwell runs bash in non-interactive mode (`bash -c`), which doesn't expand aliases by default.
+
+To enable your shell aliases, add to `~/.threadwell/agent/settings.json`:
+
+```json
+{
+  "shellCommandPrefix": "shopt -s expand_aliases\neval \"$(grep '^alias ' ~/.zshrc)\""
+}
+```
+
+Adjust the path (`~/.zshrc`, `~/.bashrc`, etc.) to match your shell config.

package/docs/skills.md

@@ -0,0 +1,232 @@
+> Threadwell can create skills. Ask it to build one for your use case.
+
+# Skills
+
+Skills are self-contained capability packages that the agent loads on-demand. A skill provides specialized workflows, setup instructions, helper scripts, and reference documentation for specific tasks.
+
+Threadwell implements the [Agent Skills standard](https://agentskills.io/specification), warning about violations but remaining lenient.
+
+## Table of Contents
+
+- [Locations](#locations)
+- [How Skills Work](#how-skills-work)
+- [Skill Commands](#skill-commands)
+- [Skill Structure](#skill-structure)
+- [Frontmatter](#frontmatter)
+- [Validation](#validation)
+- [Example](#example)
+- [Skill Repositories](#skill-repositories)
+
+## Locations
+
+> **Security:** Skills can instruct the model to perform any action and may include executable code the model invokes. Review skill content before use.
+
+Threadwell loads skills from:
+
+- Global:
+  - `~/.threadwell/agent/skills/`
+  - `~/.agents/skills/`
+- Project:
+  - `.threadwell/skills/`
+  - `.agents/skills/` in `cwd` and ancestor directories (up to git repo root, or filesystem root when not in a repo)
+- Packages: `skills/` directories or `threadwell.skills` entries in `package.json`
+- Settings: `skills` array with files or directories
+- CLI: `--skill <path>` (repeatable, additive even with `--no-skills`)
+
+Discovery rules:
+- In `~/.threadwell/agent/skills/` and `.threadwell/skills/`, direct root `.md` files are discovered as individual skills
+- In all skill locations, directories containing `SKILL.md` are discovered recursively
+- In `~/.agents/skills/` and project `.agents/skills/`, root `.md` files are ignored
+
+Disable discovery with `--no-skills` (explicit `--skill` paths still load).
+
+### Using Skills from Other Harnesses
+
+To use skills from Claude Code or OpenAI Codex, add their directories to settings:
+
+```json
+{
+  "skills": [
+    "~/.claude/skills",
+    "~/.codex/skills"
+  ]
+}
+```
+
+For project-level Claude Code skills, add to `.threadwell/settings.json`:
+
+```json
+{
+  "skills": ["../.claude/skills"]
+}
+```
+
+## How Skills Work
+
+1. At startup, Threadwell scans skill locations and extracts names and descriptions
+2. The system prompt includes available skills in XML format per the [specification](https://agentskills.io/integrate-skills)
+3. When a task matches, the agent uses `read` to load the full SKILL.md (models don't always do this; use prompting or `/skill:name` to force it)
+4. The agent follows the instructions, using relative paths to reference scripts and assets
+
+This is progressive disclosure: only descriptions are always in context, full instructions load on-demand.
+
+## Skill Commands
+
+Skills register as `/skill:name` commands:
+
+```bash
+/skill:brave-search           # Load and execute the skill
+/skill:pdf-tools extract      # Load skill with arguments
+```
+
+Arguments after the command are appended to the skill content as `User: <args>`.
+
+Toggle skill commands via `/settings` in interactive mode or in `settings.json`:
+
+```json
+{
+  "enableSkillCommands": true
+}
+```
+
+## Skill Structure
+
+A skill is a directory with a `SKILL.md` file. Everything else is freeform.
+
+```
+my-skill/
+├── SKILL.md              # Required: frontmatter + instructions
+├── scripts/              # Helper scripts
+│   └── process.sh
+├── references/           # Detailed docs loaded on-demand
+│   └── api-reference.md
+└── assets/
+    └── template.json
+```
+
+### SKILL.md Format
+
+````markdown
+---
+name: my-skill
+description: What this skill does and when to use it. Be specific.
+---
+
+# My Skill
+
+## Setup
+
+Run once before first use:
+```bash
+cd /path/to/skill && npm install
+```
+
+## Usage
+
+```bash
+./scripts/process.sh <input>
+```
+````
+
+Use relative paths from the skill directory:
+
+```markdown
+See [the reference guide](references/REFERENCE.md) for details.
+```
+
+## Frontmatter
+
+Per the [Agent Skills specification](https://agentskills.io/specification#frontmatter-required):
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `name` | Yes | Max 64 chars. Lowercase a-z, 0-9, hyphens. Must match parent directory. |
+| `description` | Yes | Max 1024 chars. What the skill does and when to use it. |
+| `license` | No | License name or reference to bundled file. |
+| `compatibility` | No | Max 500 chars. Environment requirements. |
+| `metadata` | No | Arbitrary key-value mapping. |
+| `allowed-tools` | No | Space-delimited list of pre-approved tools (experimental). |
+| `disable-model-invocation` | No | When `true`, skill is hidden from system prompt. Users must use `/skill:name`. |
+
+### Name Rules
+
+- 1-64 characters
+- Lowercase letters, numbers, hyphens only
+- No leading/trailing hyphens
+- No consecutive hyphens
+- Must match parent directory name
+
+Valid: `pdf-processing`, `data-analysis`, `code-review`
+Invalid: `PDF-Processing`, `-pdf`, `pdf--processing`
+
+### Description Best Practices
+
+The description determines when the agent loads the skill. Be specific.
+
+Good:
+```yaml
+description: Extracts text and tables from PDF files, fills PDF forms, and merges multiple PDFs. Use when working with PDF documents.
+```
+
+Poor:
+```yaml
+description: Helps with PDFs.
+```
+
+## Validation
+
+Threadwell validates skills against the Agent Skills standard. Most issues produce warnings but still load the skill:
+
+- Name doesn't match parent directory
+- Name exceeds 64 characters or contains invalid characters
+- Name starts/ends with hyphen or has consecutive hyphens
+- Description exceeds 1024 characters
+
+Unknown frontmatter fields are ignored.
+
+**Exception:** Skills with missing description are not loaded.
+
+Name collisions (same name from different locations) warn and keep the first skill found.
+
+## Example
+
+```
+brave-search/
+├── SKILL.md
+├── search.js
+└── content.js
+```
+
+**SKILL.md:**
+````markdown
+---
+name: brave-search
+description: Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content.
+---
+
+# Brave Search
+
+## Setup
+
+```bash
+cd /path/to/brave-search && npm install
+```
+
+## Search
+
+```bash
+./search.js "query"              # Basic search
+./search.js "query" --content    # Include page content
+```
+
+## Extract Page Content
+
+```bash
+./content.js https://example.com
+```
+````
+
+## Skill Repositories
+
+- [Anthropic Skills](https://github.com/anthropics/skills) - Document processing (docx, pdf, pptx, xlsx), web development
+- [Threadwell Skills](https://github.com/badlogic/threadwell-skills) - Web search, browser automation, Google APIs, transcription