indusagi-coding-agent 0.1.28 → 0.1.30

package/docs/models.md

@@ -1,193 +0,0 @@
-# Custom Models
-
-Add custom providers and models (Ollama, vLLM, LM Studio, proxies) via `~/.indusagi/agent/models.json`.
-
-## Table of Contents
-
-- [Basic Example](#basic-example)
-- [Supported APIs](#supported-apis)
-- [Provider Configuration](#provider-configuration)
-- [Model Configuration](#model-configuration)
-- [Overriding Built-in Providers](#overriding-built-in-providers)
-- [OpenAI Compatibility](#openai-compatibility)
-
-## Basic Example
-
-```json
-{
-  "providers": {
-    "ollama": {
-      "baseUrl": "http://localhost:11434/v1",
-      "api": "openai-completions",
-      "models": [
-        {
-          "id": "llama-3.1-8b",
-          "name": "Llama 3.1 8B (Local)",
-          "contextWindow": 128000,
-          "maxTokens": 32000
-        }
-      ]
-    }
-  }
-}
-```
-
-The file reloads each time you open `/model`. Edit during session; no restart needed.
-
-## Supported APIs
-
-| API | Description |
-|-----|-------------|
-| `openai-completions` | OpenAI Chat Completions (most compatible) |
-| `openai-responses` | OpenAI Responses API |
-| `anthropic-messages` | Anthropic Messages API |
-| `google-generative-ai` | Google Generative AI |
-
-Set `api` at provider level (default for all models) or model level (override per model).
-
-## Provider Configuration
-
-| Field | Description |
-|-------|-------------|
-| `baseUrl` | API endpoint URL |
-| `api` | API type (see above) |
-| `apiKey` | API key (see value resolution below) |
-| `headers` | Custom headers (see value resolution below) |
-| `authHeader` | Set `true` to add `Authorization: Bearer <apiKey>` automatically |
-| `models` | Array of model configurations |
-
-### Value Resolution
-
-The `apiKey` and `headers` fields support three formats:
-
-- **Shell command:** `"!command"` executes and uses stdout
-  ```json
-  "apiKey": "!security find-generic-password -ws 'anthropic'"
-  "apiKey": "!op read 'op://vault/item/credential'"
-  ```
-- **Environment variable:** Uses the value of the named variable
-  ```json
-  "apiKey": "MY_AINDUSAGI_KEY"
-  ```
-- **Literal value:** Used directly
-  ```json
-  "apiKey": "sk-..."
-  ```
-
-### Custom Headers
-
-```json
-{
-  "providers": {
-    "custom-proxy": {
-      "baseUrl": "https://proxy.example.com/v1",
-      "apiKey": "MY_AINDUSAGI_KEY",
-      "api": "anthropic-messages",
-      "headers": {
-        "x-portkey-api-key": "PORTKEY_AINDUSAGI_KEY",
-        "x-secret": "!op read 'op://vault/item/secret'"
-      },
-      "models": [...]
-    }
-  }
-}
-```
-
-## Model Configuration
-
-| Field | Required | Description |
-|-------|----------|-------------|
-| `id` | Yes | Model identifier |
-| `name` | No | Display name |
-| `api` | No | Override provider's API for this model |
-| `contextWindow` | No | Context window size in tokens |
-| `maxTokens` | No | Maximum output tokens |
-| `reasoning` | No | Supports extended thinking |
-| `input` | No | Input types: `["text"]` or `["text", "image"]` |
-| `cost` | No | `{"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}` |
-
-## Overriding Built-in Providers
-
-Route a built-in provider through a proxy without redefining models:
-
-```json
-{
-  "providers": {
-    "anthropic": {
-      "baseUrl": "https://my-proxy.example.com/v1"
-    }
-  }
-}
-```
-
-All built-in Anthropic models remain available. Existing OAuth or API key auth continues to work.
-
-To fully replace a built-in provider with custom models, include the `models` array:
-
-```json
-{
-  "providers": {
-    "anthropic": {
-      "baseUrl": "https://my-proxy.example.com/v1",
-      "apiKey": "ANTHROPIC_AINDUSAGI_KEY",
-      "api": "anthropic-messages",
-      "models": [...]
-    }
-  }
-}
-```
-
-## OpenAI Compatibility
-
-For providers with partial OpenAI compatibility, use the `compat` field:
-
-```json
-{
-  "providers": {
-    "local-llm": {
-      "baseUrl": "http://localhost:8080/v1",
-      "api": "openai-completions",
-      "compat": {
-        "supportsUsageInStreaming": false,
-        "maxTokensField": "max_tokens"
-      },
-      "models": [...]
-    }
-  }
-}
-```
-
-| Field | Description |
-|-------|-------------|
-| `supportsStore` | Provider supports `store` field |
-| `supportsDeveloperRole` | Use `developer` vs `system` role |
-| `supportsReasoningEffort` | Support for `reasoning_effort` parameter |
-| `supportsUsageInStreaming` | Supports `stream_options: { include_usage: true }` (default: `true`) |
-| `maxTokensField` | Use `max_completion_tokens` or `max_tokens` |
-| `openRouterRouting` | OpenRouter routing config passed to OpenRouter for model/provider selection |
-
-Example:
-
-```json
-{
-  "providers": {
-    "openrouter": {
-      "baseUrl": "https://openrouter.ai/api/v1",
-      "apiKey": "OPENROUTER_AINDUSAGI_KEY",
-      "api": "openai-completions",
-      "models": [
-        {
-          "id": "openrouter/anthropic/claude-3.5-sonnet",
-          "name": "OpenRouter Claude 3.5 Sonnet",
-          "compat": {
-            "openRouterRouting": {
-              "order": ["anthropic"],
-              "fallbacks": ["openai"]
-            }
-          }
-        }
-      ]
-    }
-  }
-}
-```

package/docs/packages.md

@@ -1,163 +0,0 @@
-> indusagi can help you create indusagi packages. Ask it to bundle your extensions, skills, prompt templates, or themes.
-
-# Indusagi Packages
-
-Indusagi packages bundle extensions, skills, prompt templates, and themes so you can share them through npm or git. A package can declare resources in `package.json` under the `indusagi` key, or use conventional directories.
-
-## Table of Contents
-
-- [Install and Manage](#install-and-manage)
-- [Package Sources](#package-sources)
-- [Creating a Indusagi Package](#creating-a-indusagi-package)
-- [Package Structure](#package-structure)
-- [Package Filtering](#package-filtering)
-- [Enable and Disable Resources](#enable-and-disable-resources)
-- [Scope and Deduplication](#scope-and-deduplication)
-
-## Install and Manage
-
-> **Security:** Indusagi packages run with full system access. Extensions execute arbitrary code, and skills can instruct the model to perform any action including running executables. Review source code before installing third-party packages.
-
-```bash
-indusagi install npm:@foo/bar@1.0.0
-indusagi install git:github.com/user/repo@v1
-indusagi install https://github.com/user/repo  # raw URLs work too
-
-indusagi remove npm:@foo/bar
-indusagi list    # show installed packages from settings
-indusagi update  # update all non-pinned packages
-```
-
-By default, `install` and `remove` write to global settings (`~/.indusagi/agent/settings.json`). Use `-l` to write to project settings (`.indusagi/settings.json`) instead. Project settings can be shared with your team, and indusagi installs any missing packages automatically on startup.
-
-To try a package without installing it, use `--extension` or `-e`. This installs to a temporary directory for the current run only:
-
-```bash
-indusagi -e npm:@foo/bar
-indusagi -e git:github.com/user/repo
-```
-
-## Package Sources
-
-Indusagi accepts three source types in settings and `indusagi install`.
-
-### npm
-
-```
-npm:@scope/pkg@1.2.3
-npm:pkg
-```
-
-- Versioned specs are pinned and skipped by `indusagi update`.
-- Global installs use `npm install -g`.
-- Project installs go under `.indusagi/npm/`.
-
-### git
-
-```
-git:github.com/user/repo@v1
-https://github.com/user/repo@v1
-```
-
-- Raw `https://` URLs work without the `git:` prefix.
-- Refs pin the package and skip `indusagi update`.
-- Cloned to `~/.indusagi/agent/git/<host>/<path>` (global) or `.indusagi/git/<host>/<path>` (project).
-- Runs `npm install` after clone or pull if `package.json` exists.
-
-### Local Paths
-
-```
-/absolute/path/to/package
-./relative/path/to/package
-```
-
-Local paths work in settings but not with `indusagi install`. If the path is a file, it loads as a single extension. If it is a directory, indusagi loads resources using package rules.
-
-## Creating a Indusagi Package
-
-Add a `indusagi` manifest to `package.json` or use conventional directories. Include the `indusagi-package` keyword for discoverability.
-
-```json
-{
-  "name": "my-package",
-  "keywords": ["indusagi-package"],
-  "indusagi": {
-    "extensions": ["./extensions"],
-    "skills": ["./skills"],
-    "prompts": ["./prompts"],
-    "themes": ["./themes"]
-  }
-}
-```
-
-Paths are relative to the package root. Arrays support glob patterns and `!exclusions`.
-
-## Package Structure
-
-### Convention Directories
-
-If no `indusagi` manifest is present, indusagi auto-discovers resources from these directories:
-
-- `extensions/` loads `.ts` and `.js` files
-- `skills/` recursively finds `SKILL.md` folders and loads top-level `.md` files as skills
-- `prompts/` loads `.md` files
-- `themes/` loads `.json` files
-
-### Bundling Other Indusagi Packages
-
-Bundle other indusagi packages by adding them as dependencies and listing them in `bundledDependencies`. Reference their resources via `node_modules/` paths.
-
-```json
-{
-  "dependencies": {
-    "shitty-extensions": "^1.0.1"
-  },
-  "bundledDependencies": ["shitty-extensions"],
-  "indusagi": {
-    "extensions": ["extensions", "node_modules/shitty-extensions/extensions"],
-    "skills": ["skills", "node_modules/shitty-extensions/skills"]
-  }
-}
-```
-
-`bundledDependencies` embeds the package in the published tarball, keeping paths stable. See `indusagi-package-test` for a working example.
-
-## Package Filtering
-
-Filter what a package loads using the object form in settings:
-
-```json
-{
-  "packages": [
-    "npm:simple-pkg",
-    {
-      "source": "npm:my-package",
-      "extensions": ["extensions/*.ts", "!extensions/legacy.ts"],
-      "skills": [],
-      "prompts": ["prompts/review.md"],
-      "themes": ["+themes/legacy.json"]
-    }
-  ]
-}
-```
-
-`+path` and `-path` are exact paths relative to the package root.
-
-- Omit a key to load all of that type.
-- Use `[]` to load none of that type.
-- `!pattern` excludes matches.
-- `+path` force-includes an exact path.
-- `-path` force-excludes an exact path.
-- Filters layer on top of the manifest. They narrow down what is already allowed.
-
-## Enable and Disable Resources
-
-Use `indusagi config` to enable or disable extensions, skills, prompt templates, and themes from installed packages and local directories. Works for both global (`~/.indusagi/agent`) and project (`.indusagi/`) scopes.
-
-## Scope and Deduplication
-
-Packages can appear in both global and project settings. If the same package appears in both, the project entry wins. Identity is determined by:
-
-- npm: package name
-- git: repository URL without ref
-- local: resolved absolute path

package/docs/prompt-templates.md

@@ -1,67 +0,0 @@
-> indusagi can create prompt templates. Ask it to build one for your workflow.
-
-# Prompt Templates
-
-Prompt templates are Markdown snippets that expand into full prompts. Type `/name` in the editor to invoke a template, where `name` is the filename without `.md`.
-
-## Locations
-
-Indusagi loads prompt templates from:
-
-- Global: `~/.indusagi/agent/prompts/*.md`
-- Project: `.indusagi/prompts/*.md`
-- Packages: `prompts/` directories or `indusagi.prompts` entries in `package.json`
-- Settings: `prompts` array with files or directories
-- CLI: `--prompt-template <path>` (repeatable)
-
-Disable discovery with `--no-prompt-templates`.
-
-## Format
-
-```markdown
----
-description: Review staged git changes
----
-Review the staged changes (`git diff --cached`). Focus on:
-- Bugs and logic errors
-- Security issues
-- Error handling gaps
-```
-
-- The filename becomes the command name. `review.md` becomes `/review`.
-- `description` is optional. If missing, the first non-empty line is used.
-
-## Usage
-
-Type `/` followed by the template name in the editor. Autocomplete shows available templates with descriptions.
-
-```
-/review                           # Expands review.md
-/component Button                 # Expands with argument
-/component Button "click handler" # Multiple arguments
-```
-
-## Arguments
-
-Templates support positional arguments and simple slicing:
-
-- `$1`, `$2`, ... positional args
-- `$@` or `$ARGUMENTS` for all args joined
-- `${@:N}` for args from the Nth position (1-indexed)
-- `${@:N:L}` for `L` args starting at N
-
-Example:
-
-```markdown
----
-description: Create a component
----
-Create a React component named $1 with features: $@
-```
-
-Usage: `/component Button "onClick handler" "disabled support"`
-
-## Loading Rules
-
-- Template discovery in `prompts/` is non-recursive.
-- If you want templates in subdirectories, add them explicitly via `prompts` settings or a package manifest.

package/docs/providers.md

@@ -1,147 +0,0 @@
-# Providers
-
-Indusagi supports subscription-based providers via OAuth and API key providers via environment variables or auth file. For each provider, indusagi knows all available models. The list is updated with every indusagi release.
-
-## Table of Contents
-
-- [Subscriptions](#subscriptions)
-- [API Keys](#api-keys)
-- [Auth File](#auth-file)
-- [Cloud Providers](#cloud-providers)
-- [Custom Providers](#custom-providers)
-- [Resolution Order](#resolution-order)
-
-## Subscriptions
-
-Use `/login` in interactive mode, then select a provider:
-
-- Claude Pro/Max
-- ChatGPT Plus/Pro (Codex)
-- GitHub Copilot
-- Google Gemini CLI
-- Google Antigravity
-
-Use `/logout` to clear credentials. Tokens are stored in `~/.indusagi/agent/auth.json` and auto-refresh when expired.
-
-### GitHub Copilot
-
-- Press Enter for github.com, or enter your GitHub Enterprise Server domain
-- If you get "model not supported", enable it in VS Code: Copilot Chat → model selector → select model → "Enable"
-
-### Google Providers
-
-- **Gemini CLI**: Standard Gemini models via Cloud Code Assist
-- **Antigravity**: Sandbox with Gemini 3, Claude, and GPT-OSS models
-- Both free with any Google account, subject to rate limits
-- For paid Cloud Code Assist: set `GOOGLE_CLOUD_PROJECT` env var
-
-### OpenAI Codex
-
-- Requires ChatGPT Plus or Pro subscription
-- Personal use only; for production, use the OpenAI Platform API
-
-## API Keys
-
-Set via environment variable:
-
-```bash
-export ANTHROPIC_AINDUSAGI_KEY=sk-ant-...
-indusagi
-```
-
-| Provider | Environment Variable |
-|----------|---------------------|
-| Anthropic | `ANTHROPIC_AINDUSAGI_KEY` |
-| OpenAI | `OPENAI_AINDUSAGI_KEY` |
-| Google Gemini | `GEMINI_AINDUSAGI_KEY` |
-| Mistral | `MISTRAL_AINDUSAGI_KEY` |
-| Groq | `GROQ_AINDUSAGI_KEY` |
-| Cerebras | `CEREBRAS_AINDUSAGI_KEY` |
-| xAI | `XAI_AINDUSAGI_KEY` |
-| OpenRouter | `OPENROUTER_AINDUSAGI_KEY` |
-| Vercel AI Gateway | `AI_GATEWAY_AINDUSAGI_KEY` |
-| ZAI | `ZAI_AINDUSAGI_KEY` |
-| OpenCode Zen | `OPENCODE_AINDUSAGI_KEY` |
-| MiniMax | `MINIMAX_AINDUSAGI_KEY` |
-| MiniMax (China) | `MINIMAX_CN_AINDUSAGI_KEY` |
-
-## Auth File
-
-Store credentials in `~/.indusagi/agent/auth.json`:
-
-```json
-{
-  "anthropic": { "type": "api_key", "key": "sk-ant-..." },
-  "openai": { "type": "api_key", "key": "sk-..." },
-  "google": { "type": "api_key", "key": "..." }
-}
-```
-
-The file is created with `0600` permissions (user read/write only). Auth file credentials take priority over environment variables.
-
-OAuth credentials are also stored here after `/login` and managed automatically.
-
-## Cloud Providers
-
-### Azure OpenAI
-
-```bash
-export AZURE_OPENAI_AINDUSAGI_KEY=...
-export AZURE_OPENAI_BASE_URL=https://your-resource.openai.azure.com
-# or use resource name instead of base URL
-export AZURE_OPENAI_RESOURCE_NAME=your-resource
-
-# Optional
-export AZURE_OPENAI_AINDUSAGI_VERSION=2024-02-01
-export AZURE_OPENAI_DEPLOYMENT_NAME_MAP=gpt-4=my-gpt4,gpt-4o=my-gpt4o
-```
-
-### Amazon Bedrock
-
-```bash
-# Option 1: AWS Profile
-export AWS_PROFILE=your-profile
-
-# Option 2: IAM Keys
-export AWS_ACCESS_KEY_ID=AKIA...
-export AWS_SECRET_ACCESS_KEY=...
-
-# Option 3: Bearer Token
-export AWS_BEARER_TOKEN_BEDROCK=...
-
-# Optional region (defaults to us-east-1)
-export AWS_REGION=us-west-2
-```
-
-Also supports ECS task roles (`AWS_CONTAINER_CREDENTIALS_*`) and IRSA (`AWS_WEB_IDENTITY_TOKEN_FILE`).
-
-```bash
-indusagi --provider amazon-bedrock --model us.anthropic.claude-sonnet-4-20250514-v1:0
-```
-
-### Google Vertex AI
-
-Uses Application Default Credentials:
-
-```bash
-gcloud auth application-default login
-export GOOGLE_CLOUD_PROJECT=your-project
-export GOOGLE_CLOUD_LOCATION=us-central1
-```
-
-Or set `GOOGLE_APPLICATION_CREDENTIALS` to a service account key file.
-
-## Custom Providers
-
-**Via models.json:** Add Ollama, LM Studio, vLLM, or any provider that speaks a supported API (OpenAI Completions, OpenAI Responses, Anthropic Messages, Google Generative AI). See [models.md](models.md).
-
-**Via extensions:** For providers that need custom API implementations or OAuth flows, create an extension. See [custom-provider.md](custom-provider.md) and [examples/extensions/custom-provider-gitlab-duo](../examples/extensions/custom-provider-gitlab-duo/).
-
-## Resolution Order
-
-When resolving credentials for a provider:
-
-1. CLI `--api-key` flag
-2. `auth.json` entry (API key or OAuth token)
-3. Environment variable
-4. Custom provider keys from `models.json`