# dagu - Doramagic AI Context Pack > Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated. ## Sufficiency Principle - **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary. - **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work. ## How the Host AI Should Use This You are reading the AI Context Pack that Doramagic compiled for dagu. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project. ## Claim Consumption Rules - **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure. - **Minimum status for a fact**: `supported` - `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path. - `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying. - `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact. - `unverified`: Must not be used as fact; state clearly that evidence is insufficient. - `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf. ## Who It Fits Best - **Developers already using host AIs such as Claude/Codex/Cursor/Gemini**: The README or plugin config mentions multiple host AIs. Evidence: `README.md` Claim: `clm_0003` supported 0.86 - **Users who want to bring professional workflows into a host AI**: The repo contains Skill documents. Evidence: `skills/dagu/SKILL.md` Claim: `clm_0004` supported 0.86 ## What It Can Do - **AI Skill / Agent Instruction Asset Library** (Previewable before install): The project contains Skill or Agent instruction files that a host AI can read, useful for bringing professional workflows into hosts like Claude, Codex, or Cursor. Evidence: `skills/dagu/SKILL.md` Claim: `clm_0001` supported 0.86 - **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `README.md` Claim: `clm_0002` supported 0.86 ## How to Start - `curl -fsSL https://raw.githubusercontent.com/dagucloud/dagu/main/scripts/installer.sh | bash` Evidence: `README.md` Claim: `clm_0005` supported 0.86 - `git clone https://github.com/dagucloud/dagu.git && cd dagu` Evidence: `README.md` Claim: `clm_0006` supported 0.86 ## Continue-or-Stop Decision Card - **Current recommendation**: Needs admin / security approval - **Why**: Continuing may involve secrets, accounts, external services, or sensitive context; get admin or security approval first. ### 30-Second Read - **What to do now**: Needs admin / security approval - **Minimum safe next step**: Run Prompt Preview first; if credentials or an enterprise environment are involved, get approval before trialing - **Do not trust yet**: Real output quality cannot be trusted before install. - **Continuing will touch**: Command execution, Host AI configuration, Local environment or project files ### What You Can Trust Now - **Target-audience signal: Developers already using host AIs such as Claude/Codex/Cursor/Gemini** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0003` supported 0.86 - **Target-audience signal: Users who want to bring professional workflows into a host AI** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `skills/dagu/SKILL.md` Claim: `clm_0004` supported 0.86 - **Capability exists: AI Skill / Agent Instruction Asset Library** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `skills/dagu/SKILL.md` Claim: `clm_0001` supported 0.86 - **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `README.md` Claim: `clm_0002` supported 0.86 - **There are Quick Start / install-command signals** (supported): You can trust that the docs mention a startup or install entrypoint; do not run it directly in your primary environment because of that. Evidence: `README.md` Claim: `clm_0005` supported 0.86 ### What You Cannot Trust Yet - **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project. - **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment. - **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior. Evidence: `CLAUDE.md`, `skills/dagu/SKILL.md` - **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first. - **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment. - **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. - **Do the install commands require network access, permissions, or global writes?** (unverified): This affects install risk in both enterprise and personal environments. Evidence: `README.md` ### What Continuing Will Touch - **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `README.md` - **Host AI configuration**: The plugin, Skill, or rule-loading config of hosts like Claude/Codex/Cursor/Gemini/OpenCode. Why: Host configuration changes how the AI works afterward and may conflict with the user's existing rules. Evidence: `CLAUDE.md`, `skills/dagu/SKILL.md` - **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `README.md` - **Environment variables / API keys**: Project entry docs explicitly showing API key, token, secret, or account credential configuration. Why: If a real install needs credentials, use test credentials first and go through a permission/compliance review. Evidence: `README.md` - **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts. ### Minimum Safe Next Steps - **Run Prompt Preview first**: Use a pre-install interactive trial to judge whether the way of working fits; it needs no authorization or environment change. (applies when: Applies to any project, especially when output quality is unknown.) - **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.) - **Back up your host AI configuration first**: Skill, plugin, and rule files may change the default behavior of Claude/Cursor/Codex. (applies when: When there is a plugin manifest, a Skill, or a host rule entrypoint.) - **Do not use real production credentials**: Once an environment variable / API key enters the host or toolchain, it can create account and compliance risk. (applies when: When environment signals like API, TOKEN, KEY, or SECRET appear.) - **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.) ### Exit Plan - **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable. - **Be ready to remove the host plugin / Skill / rule entrypoint**: If behavior is off after the trial install, you can restore the host AI to its pre-trial state. - **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually. - **Be ready to revoke test API keys or tokens**: If test credentials leak or are misused, you can cut losses quickly. - **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck. ## What Can Only Be Previewed - Explain who the project fits and what it can do - Demonstrate a typical conversation flow based on project docs - Help the user decide whether it is worth installing or researching further ## What Must Be Verified After Install - Actually installing the Skill, plugin, or CLI - Running scripts, modifying local files, or accessing external services - Verifying real output quality, performance, and compatibility ## Boundary & Risk Decision Card - **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0007` inferred 0.45 - **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `README.md` Claim: `clm_0008` supported 0.86 - **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment. - **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. - **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments. ## Pre-Work Working Context ### Loading Order - First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset. - Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative. - Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match. - When you need to carry out a concrete task, check role_skill_index first, then evidence_index. - For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required. ### Task Routes - **AI Skill / Agent Instruction Asset Library**: Use role_skill_index / evidence_index to help the user pick a usable role, Skill, or workflow first. Boundary: Can be experienced via a pre-install Prompt. Evidence: `skills/dagu/SKILL.md` Claim: `clm_0001` supported 0.86 - **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `README.md` Claim: `clm_0002` supported 0.86 ### Context Scale - Total files: 2330 - Important-file coverage: 40/2330 - Evidence index entries: 63 - Role / Skill entries: 1 ### Handling Insufficient Evidence - **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts. - **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install. - **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run. - **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version. ## Prompt Recipes ### Fit assessment - Goal: Judge whether this project fits the user's current task. - Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation. ```text Based on the AI Context Pack for dagu, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id. ``` ### Pre-install experience - Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise. - Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language. ```text Treat dagu as a pre-install experience asset, not an already-installed tool or a real runtime environment. Output exactly four parts: 1. Ask me 3 necessary questions first. 2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow. 3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run. 4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project. Hard boundaries: - Do not claim you have installed, run, executed tests, modified files, or produced real results. - Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing". - If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...". - The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating". - Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment. - Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions. ``` ### Role / Skill selection - Goal: Pick the best-matching asset from the project's roles or Skills. - Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed. ```text Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs. ``` ### Risk pre-check - Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting. - Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items. ```text Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have. ``` ### Host AI kickoff instruction - Goal: Turn the project context into a host AI instruction for the start of a conversation. - Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI. ```text Based on the AI Context Pack for dagu, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results. ``` ## Role / Skill Index - Indexed 1 role / Skill / project-doc entries. - **dagu** (skill): Writes, validates, and debugs DAG workflow definitions in YAML. Use when creating, editing, or troubleshooting DAGs. Activation hint: When the user's task is highly relevant to the workflow described by “dagu”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/dagu/SKILL.md` ## Evidence Index - Indexed 63 evidence entries. - **Quick Look** (documentation): Dagu is a local-first workflow engine for ops automation and AI-assisted operations. It is open source and self-hostable: a single binary with a built-in Web UI, no external database or message broker, running on Linux / Mac / Windows. Define DAGs https://en.wikipedia.org/wiki/Directed acyclic graph in a declarative YAML format. It natively supports shell commands, Docker containers, Kubernetes Jobs, remote commands via SSH, external coding-agent CLIs through harness.run , and more through Dagu Actions. Evidence: `README.md` - **NPM Packages for Dagu** (documentation): This directory contains the npm package structure for distributing Dagu binaries via npm. Evidence: `npm/README.md` - **Bundled Skills** (documentation): This directory is the source of truth for the skills shipped inside the Dagu binary. Evidence: `skills/README.md` - **UI** (documentation): - Node.js latest stable version - pnpm Evidence: `ui/README.md` - **Dagu Helm Chart** (documentation): A Helm chart for deploying Dagu on Kubernetes. Evidence: `charts/dagu/README.md` - **Docker Assets** (documentation): This directory hosts Docker-centric deployment assets for Dagu. Evidence: `deploy/docker/README.md` - **Dagu Kubernetes Local Setup** (documentation): This directory contains Kubernetes manifests for running Dagu in distributed mode on your local machine for testing purposes. Evidence: `deploy/k8s/README.md` - **Embedded Dagu Examples** (documentation): These examples show how another Go application can import Dagu as a library: Evidence: `examples/embedded/README.md` - **Keepalive** (documentation): A minimal binary that keeps containers running by waiting for termination signals SIGTERM, SIGINT . Evidence: `internal/runtime/builtin/docker/keepalive/README.md` - **@dagucloud/dagu-darwin-arm64** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-darwin-arm64/README.md` - **@dagucloud/dagu-freebsd-arm64** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-freebsd-arm64/README.md` - **@dagucloud/dagu-linux-armv7** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-linux-armv7/README.md` - **@dagucloud/dagu-linux-ppc64** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-linux-ppc64/README.md` - **@dagucloud/dagu-linux-s390x** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-linux-s390x/README.md` - **@dagucloud/dagu-linux-x64** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-linux-x64/README.md` - **@dagucloud/dagu-openbsd-arm64** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-openbsd-arm64/README.md` - **@dagucloud/dagu-openbsd-x64** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-openbsd-x64/README.md` - **@dagucloud/dagu-win32-arm64** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-win32-arm64/README.md` - **@dagucloud/dagu-win32-x64** (documentation): Platform-specific binary package for Dagu. Evidence: `npm/dagu-win32-x64/README.md` - **@dagucloud/dagu** (documentation): A powerful Workflow Orchestration Engine with simple declarative YAML API Evidence: `npm/dagu/README.md` - **UI Component Layer** (documentation): Use @/components/ui/ as the only shared component-library import path. Evidence: `ui/src/components/ui/README.md` - **DAG Components** (documentation): This directory contains components for the DAG Directed Acyclic Graph feature of the application. The components have been organized into logical groups to improve maintainability and code organization. Evidence: `ui/src/features/dags/components/README.md` - **CLAUDE.md** (documentation): This file provides guidance to Claude Code claude.ai/code when working with code in this repository. Evidence: `CLAUDE.md` - **🎯 What is Dagu?** (documentation): Dagu is a modern, powerful, yet surprisingly simple workflow orchestration engine that runs as a single binary with zero external dependencies. Born from the frustration of managing hundreds of legacy cron jobs scattered across multiple servers, Dagu brings clarity, visibility, and control to workflow automation. Evidence: `ui/CLAUDE.md` - **Package** (package_manifest): { "name": "dagu", "version": "1.0.0", "description": "Web UI for Dagu", "private": true, "engines": { "node": " =18.18.0" }, "scripts": { "build": "webpack --config webpack.prod.js", "test": "vitest run", "test:e2e": "playwright test", "test:e2e:headed": "playwright test --headed", "test:e2e:debug": "playwright test --debug", "test:e2e:install": "playwright install chromium", "dev": "webpack-dev-server --config webpack.dev.js", "lint": "eslint --fix --ext .ts,.tsx .", "prettier": "prettier --write src/ / .ts x ", "typecheck": "tsc", "typecheck:watch": "tsc -w", "profile": "webpack --profile --config webpack.prod.js --json=compilation-stats.json && webpack-bundle-analyzer ./compilation-stats… Evidence: `ui/package.json` - **Contributing to Dagu** (documentation): Thank you for considering to help improve Dagu! We welcome contributions from anyone on the internet. Evidence: `CONTRIBUTING.md` - **Package** (package_manifest): { "name": "@dagucloud/dagu-darwin-arm64", "version": "0.0.0-development", "description": "Dagu binary for macOS ARM64 Apple Silicon ", "keywords": "dagu", "workflow", "darwin", "macos", "arm64", "apple-silicon" , "homepage": "https://github.com/dagucloud/dagu", "repository": { "type": "git", "url": "git+https://github.com/dagucloud/dagu.git" }, "license": "GPL-3.0", "author": "Dagu Contributors", "os": "darwin" , "cpu": "arm64" , "bin": { "dagu": "./bin/dagu" }, "files": "bin/dagu" , "publishConfig": { "access": "public" } } Evidence: `npm/dagu-darwin-arm64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-darwin-x64", "version": "0.0.0-development", "description": "Dagu binary for macOS x64", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "darwin" , "cpu": "x64" , "files": "bin/dagu" } Evidence: `npm/dagu-darwin-x64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-freebsd-arm64", "version": "0.0.0-development", "description": "Dagu binary for FreeBSD ARM64", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "freebsd" , "cpu": "arm64" , "files": "bin/dagu" } Evidence: `npm/dagu-freebsd-arm64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-freebsd-x64", "version": "0.0.0-development", "description": "Dagu binary for FreeBSD x64", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "freebsd" , "cpu": "x64" , "files": "bin/dagu" } Evidence: `npm/dagu-freebsd-x64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-linux-arm64", "version": "0.0.0-development", "description": "Dagu binary for Linux ARM64", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "linux" , "cpu": "arm64" , "files": "bin/dagu" } Evidence: `npm/dagu-linux-arm64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-linux-armv6", "version": "0.0.0-development", "description": "Dagu binary for Linux ARMv6", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "linux" , "cpu": "arm" , "files": "bin/dagu" } Evidence: `npm/dagu-linux-armv6/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-linux-armv7", "version": "0.0.0-development", "description": "Dagu binary for Linux ARMv7 32-bit ARM ", "keywords": "dagu", "workflow", "linux", "arm", "armv7", "raspberry-pi" , "homepage": "https://github.com/dagucloud/dagu", "repository": { "type": "git", "url": "git+https://github.com/dagucloud/dagu.git" }, "license": "GPL-3.0", "author": "Dagu Contributors", "os": "linux" , "cpu": "arm" , "bin": { "dagu": "./bin/dagu" }, "files": "bin/dagu" , "publishConfig": { "access": "public" } } Evidence: `npm/dagu-linux-armv7/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-linux-ia32", "version": "0.0.0-development", "description": "Dagu binary for Linux 32-bit", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "linux" , "cpu": "ia32" , "files": "bin/dagu" } Evidence: `npm/dagu-linux-ia32/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-linux-ppc64", "version": "0.0.0-development", "description": "Dagu binary for Linux PowerPC 64-bit", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "linux" , "cpu": "ppc64" , "files": "bin/dagu" } Evidence: `npm/dagu-linux-ppc64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-linux-s390x", "version": "0.0.0-development", "description": "Dagu binary for Linux s390x", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "linux" , "cpu": "s390x" , "files": "bin/dagu" } Evidence: `npm/dagu-linux-s390x/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-linux-x64", "version": "0.0.0-development", "description": "Dagu binary for Linux x64", "keywords": "dagu", "workflow", "linux", "x64" , "homepage": "https://github.com/dagucloud/dagu", "repository": { "type": "git", "url": "git+https://github.com/dagucloud/dagu.git" }, "license": "GPL-3.0", "author": "Dagu Contributors", "os": "linux" , "cpu": "x64" , "bin": { "dagu": "./bin/dagu" }, "files": "bin/dagu" , "publishConfig": { "access": "public" } } Evidence: `npm/dagu-linux-x64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-openbsd-arm64", "version": "0.0.0-development", "description": "Dagu binary for OpenBSD ARM64", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "openbsd" , "cpu": "arm64" , "files": "bin/dagu" } Evidence: `npm/dagu-openbsd-arm64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-openbsd-x64", "version": "0.0.0-development", "description": "Dagu binary for OpenBSD x64", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "openbsd" , "cpu": "x64" , "files": "bin/dagu" } Evidence: `npm/dagu-openbsd-x64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-win32-arm64", "version": "0.0.0-development", "description": "Dagu binary for Windows ARM64", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "win32" , "cpu": "arm64" , "files": "bin/dagu.exe" } Evidence: `npm/dagu-win32-arm64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-win32-ia32", "version": "0.0.0-development", "description": "Dagu binary for Windows 32-bit", "repository": "github:dagucloud/dagu", "license": "GPL-3.0", "os": "win32" , "cpu": "ia32" , "files": "bin/dagu.exe" } Evidence: `npm/dagu-win32-ia32/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu-win32-x64", "version": "0.0.0-development", "description": "Dagu binary for Windows x64", "keywords": "dagu", "workflow", "windows", "win32", "x64" , "homepage": "https://github.com/dagucloud/dagu", "repository": { "type": "git", "url": "git+https://github.com/dagucloud/dagu.git" }, "license": "GPL-3.0", "author": "Dagu Contributors", "os": "win32" , "cpu": "x64" , "bin": { "dagu": "./bin/dagu.exe" }, "files": "bin/dagu.exe" , "publishConfig": { "access": "public" } } Evidence: `npm/dagu-win32-x64/package.json` - **Package** (package_manifest): { "name": "@dagucloud/dagu", "version": "0.0.0-development", "description": "A powerful Workflow Orchestration Engine with simple declarative YAML API. Zero-dependency, single binary for Linux, macOS, and Windows.", "keywords": "workflow", "automation", "orchestration", "dag", "pipeline", "scheduler", "task-runner", "workflow-engine", "devops", "ci-cd" , "homepage": "https://github.com/dagucloud/dagu", "bugs": { "url": "https://github.com/dagucloud/dagu/issues" }, "repository": { "type": "git", "url": "git+https://github.com/dagucloud/dagu.git" }, "license": "GPL-3.0", "author": "Dagu Contributors", "bin": { "dagu": "bin/cli" }, "scripts": { "postinstall": "node ./install.js" }, "dependenci… Evidence: `npm/dagu/package.json` - **DAG Authoring** (skill_instruction): Load only the reference file that matches the task. Evidence: `skills/dagu/SKILL.md` - **License** (source_file): GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007 Evidence: `LICENSE` - **Dagrunurls** (source_file): type DAGRunPageURLInput = { rootDAGRunName: string; rootDAGRunId: string; remoteNode: string; subDAGRunId?: string; step?: string; }; ⋮---- type DAGPageURLInput = { fileName: string; remoteNode: string; tab?: string; rootDAGRunName?: string; rootDAGRunId?: string; subDAGRunId?: string; step?: string; }; ⋮---- function appendQuery path: string, params: URLSearchParams : string ⋮---- export function buildDAGRunPageURL { rootDAGRunName, rootDAGRunId, remoteNode, subDAGRunId, step, }: DAGRunPageURLInput : string ⋮---- export function buildDAGPageURL { fileName, remoteNode, tab, rootDAGRunName, rootDAGRunId, subDAGRunId, step, }: DAGPageURLInput : string Evidence: `ui/src/features/dag-runs/lib/dagRunUrls.ts` - **Manualactionstate** (source_file): import { components, NodeStatus, Status } from '@/api/v1/schema'; ⋮---- type DAGRun = components 'schemas' 'DAGRunSummary' components 'schemas' 'DAGRunDetails' ; type DAGRunDetails = components 'schemas' 'DAGRunDetails' ; type DAGRunNode = DAGRunDetails 'nodes' number ; ⋮---- type ManualActionState = { isWaiting: boolean; waitingApprovalNodes: DAGRunNode ; waitingHumanTaskNodes: DAGRunNode ; hasHumanTaskWork: boolean; }; ⋮---- function hasNodeDetails dagRun: DAGRun : dagRun is DAGRunDetails ⋮---- export function getManualActionState dagRun?: DAGRun : ManualActionState Evidence: `ui/src/features/dag-runs/lib/manualActionState.ts` - **Geteventhandlers** (source_file): import { components } from '../../../api/v1/schema'; ⋮---- export function getEventHandlers s: components 'schemas' 'DAGRunDetails' Evidence: `ui/src/features/dags/lib/getEventHandlers.ts` - **Nodestatus** (source_file): import { components, NodeStatus, NodeStatusLabel, } from '../../../api/v1/schema'; ⋮---- function nodeStatusLabel status: NodeStatus : NodeStatusLabel ⋮---- function updateRequiredNodeStatus node: components 'schemas' 'Node' , stepName: string, status: NodeStatus : components 'schemas' 'Node' ⋮---- function updateOptionalNodeStatus node: components 'schemas' 'Node' undefined, stepName: string, status: NodeStatus : components 'schemas' 'Node' undefined ⋮---- export function updateDAGRunNodeStatus dagRun: components 'schemas' 'DAGRunDetails' , stepName: string, status: NodeStatus : components 'schemas' 'DAGRunDetails' ⋮---- export function updateDAGRunsNodeStatus dagRuns: components 'schemas'… Evidence: `ui/src/features/dags/lib/nodeStatus.ts` - **Ansi** (source_file): import React from 'react'; ⋮---- export function stripAnsi text: string : string ⋮---- type TextStyle = { color?: string; background?: string; bold?: boolean; dim?: boolean; italic?: boolean; underline?: boolean; }; ⋮---- export type AnsiSegment = { text: string; style: TextStyle; }; ⋮---- // Base 16 palette tuned to stay legible on both light and dark backgrounds. ⋮---- function color256 n: number : string undefined ⋮---- function applySgr prev: TextStyle, params: string : TextStyle ⋮---- export function parseAnsi line: string : AnsiSegment ⋮---- function toCssProperties style: TextStyle : React.CSSProperties undefined ⋮---- function highlightParts text: string, highlight: string, keyBase:… Evidence: `ui/src/lib/ansi.tsx` - **Authheaders** (source_file): import { getAuthToken } from './authSession'; ⋮---- export function getAuthHeaders additionalHeaders?: Record : Record Evidence: `ui/src/lib/authHeaders.ts` - **Authsession** (source_file): type AuthSessionReason = 'login' 'logout' 'setup' 'external' 'expired' 'unauthorized'; ⋮---- export type AuthSessionChange = { token: string null; expiresAt: string null; reason: AuthSessionReason; }; ⋮---- function dispatchSessionChange change: AuthSessionChange : void ⋮---- function readRuntimeAuthMode : string undefined ⋮---- export function isBuiltinAuthMode : boolean ⋮---- function parseExpiresAt value: string null : number null ⋮---- function base64URLDecode value: string : string ⋮---- function decodeJWTExpiresAt token: string : string null ⋮---- export function setAuthSession token: string, expiresAt?: string null, reason: AuthSessionReason = 'login' : void ⋮---- export function cle… Evidence: `ui/src/lib/authSession.ts` - **Dag Validation** (source_file): export function validateDAGName name: string : ⋮---- export function isValidDAGName name: string : boolean Evidence: `ui/src/lib/dag-validation.ts` - **Dagruntiming** (source_file): import dayjs from './dayjs'; ⋮---- type DAGRunTiming = { scheduleTime?: string; queuedAt?: string; }; ⋮---- export function getDAGRunScheduleSortValue run: DAGRunTiming : number Evidence: `ui/src/lib/dagRunTiming.ts` - **Code of Conduct** (documentation): This project is covered under the Go Community Code of Conduct https://golang.org/conduct . Evidence: `CODE_OF_CONDUCT.md` - **Licensing** (documentation): Dagu source code is distributed under the GNU General Public License version 3 or later GPL-3.0-or-later . See LICENSE ./LICENSE . Evidence: `LICENSING.md` - **Dagu Workflow Schema at a Glance** (documentation): This is the repository-level overview of Dagu's workflow YAML schema. It is meant to help a visitor understand how a workflow is shaped, what the current canonical syntax is, and where to look when they need the full field-level reference. Evidence: `README_SCHEMA.md` - **Schema v2 Migration Guide** (documentation): v1 v2 ---- ---- command: echo hello run: echo hello multi-line command: run: script: run: shell , shell args , shell packages move under with: on the run: step exec: action: exec with with.command and with.args type: http action: http.request type: ssh + command action: ssh.run with with.command type: postgres + command action: postgres.query with with.query type: sqlite + command action: sqlite.query with with.query SQL import config action: postgres.import or action: sqlite.import type: jq + command action: jq.filter with with.filter type: docker action: docker.run type: container action: container.run type: k8s or type: kubernetes action: k8s.run or action: kubernetes.run call: + params:… Evidence: `SCHEMA_MIGRATION.md` - **Security Policy** (documentation): Dagu security fixes are provided for the current development branch and the latest stable release series. Evidence: `SECURITY.md` - **Dark Mode Implementation Requirements Document** (documentation): Dark Mode Implementation Requirements Document Evidence: `ui/DARK_MODE_REQUIREMENTS.md` - The remaining 3 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`. ## Rules the Host AI Must Follow - **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `README.md`, `npm/README.md`, `skills/README.md` - **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `README.md`, `npm/README.md`, `skills/README.md` ## Questions the User Should Answer First - Which host AI or local environment do you plan to use it in? - Do you just want to experience the workflow first, or are you ready to actually install? - What matters most to you: install cost, output quality, or conflicts with your existing rules? ## Acceptance Checks - Every capability claim can be traced back to a file path in evidence_refs. - AI_CONTEXT_PACK.md does not package previews as a real run. - The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes. --- ## Doramagic Context Augmentation The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints. ## Human Manual Outline Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph. Host AI hard rules: - Do not treat page titles, section order, summaries, or importance values as factual project evidence. - When explaining the Human Manual outline, state that it is only a reading route or salience signal. - Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph. - **Overview**: importance `high` - source_paths: Dockerfile, README.md, charts/dagu/README.md, deploy/docker/README.md, deploy/k8s/README.md - **Lib**: importance `high` - source_paths: ui/src/lib/ansi.tsx, ui/src/lib/authHeaders.ts, ui/src/lib/authSession.ts, ui/src/lib/constants.ts, ui/src/lib/dag-validation.ts - **Lib**: importance `high` - source_paths: ui/src/features/dag-runs/lib/dagRunUrls.ts, ui/src/features/dag-runs/lib/manualActionState.ts - **Lib**: importance `high` - source_paths: ui/src/features/dags/lib/getEventHandlers.ts, ui/src/features/dags/lib/nodeStatus.ts ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `c5ecdccf22dfdb52d586f783cc63f4d94d07acd9` - inspected_files: `Dockerfile`, `README.md`, `examples/embedded/README.md`, `examples/embedded/custom-executor/workflow.yaml`, `examples/embedded/distributed/workflow.yaml`, `examples/embedded/local/workflow.yaml` Host AI hard rules: - Without repo_clone_verified=true, do not claim that the source code has been read. - Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts. - Without quick_start_verified=true, do not claim that the Quick Start path has run successfully. ## Doramagic Pitfall Constraints These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes. ### Constraint 1: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: bug: `stdout.outputs` declared on a `handler_on` step is captured but never published to the DAG run outputs - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: bug: `stdout.outputs` declared on a `handler_on` step is captured but never published to the DAG run outputs. Context: Observed when using node, python, linux - Why it matters: Developers may fail before the first successful local run: bug: `stdout.outputs` declared on a `handler_on` step is captured but never published to the DAG run outputs - Evidence: failure_mode_cluster:github_issue | https://github.com/dagucloud/dagu/issues/2428 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 2: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: bug: queued run that fails before startup is never dequeued and retries forever - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: bug: queued run that fails before startup is never dequeued and retries forever. Context: Observed when using macos - Why it matters: Developers may fail before the first successful local run: bug: queued run that fails before startup is never dequeued and retries forever - Evidence: failure_mode_cluster:github_issue | https://github.com/dagucloud/dagu/issues/2436 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 3: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: helm-dagu-1.0.10 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: helm-dagu-1.0.10. Context: Observed during installation or first-run setup. - Why it matters: Upgrade or migration may change expected behavior: helm-dagu-1.0.10 - Evidence: failure_mode_cluster:github_release | https://github.com/dagucloud/dagu/releases/tag/helm-dagu-1.0.10 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 4: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: helm-dagu-1.0.11 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: helm-dagu-1.0.11. Context: Observed during installation or first-run setup. - Why it matters: Upgrade or migration may change expected behavior: helm-dagu-1.0.11 - Evidence: failure_mode_cluster:github_release | https://github.com/dagucloud/dagu/releases/tag/helm-dagu-1.0.11 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 5: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: question: `onInit` handler is recorded but never displayed — is that intended? - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: question: `onInit` handler is recorded but never displayed — is that intended?. Context: Observed when using python, linux - Why it matters: Developers may fail before the first successful local run: question: `onInit` handler is recorded but never displayed — is that intended? - Evidence: failure_mode_cluster:github_issue | https://github.com/dagucloud/dagu/issues/2429 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 6: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: v2.10.0 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v2.10.0. Context: Observed during installation or first-run setup. - Why it matters: Upgrade or migration may change expected behavior: v2.10.0 - Evidence: failure_mode_cluster:github_release | https://github.com/dagucloud/dagu/releases/tag/v2.10.0 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.