# neuralgentics - 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 neuralgentics. 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: `.opencode/skills/boomerang-handoff/SKILL.md`, `.opencode/skills/boomerang-orchestrator/SKILL.md`, `.opencode/skills/external-skills-fetcher/SKILL.md`, `.opencode/skills/kanban-board-manager/SKILL.md` et al. 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: `.opencode/skills/boomerang-handoff/SKILL.md`, `.opencode/skills/boomerang-orchestrator/SKILL.md`, `.opencode/skills/external-skills-fetcher/SKILL.md`, `.opencode/skills/kanban-board-manager/SKILL.md` et al. 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: `AGENTS.md`, `README.md` Claim: `clm_0002` supported 0.86 ## How to Start - `curl -fsSL https://raw.githubusercontent.com/Veedubin/neuralgentics/main/scripts/install.sh | bash` Evidence: `README.md` Claim: `clm_0005` supported 0.86, `clm_0007` supported 0.86 - `curl -LsSf https://astral.sh/uv/install.sh | sh` Evidence: `README.md` Claim: `clm_0006` supported 0.86 - `curl -fsSL https://raw.githubusercontent.com/Veedubin/neuralgentics/main/scripts/install.sh | bash -s -- --home-dir` Evidence: `AGENTS.md` Claim: `clm_0007` 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**: Research conclusions, citations, and experiment results cannot be trusted before install. - **Continuing will touch**: Research judgment, Command execution, Host AI configuration ### 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: `.opencode/skills/boomerang-handoff/SKILL.md`, `.opencode/skills/boomerang-orchestrator/SKILL.md`, `.opencode/skills/external-skills-fetcher/SKILL.md`, `.opencode/skills/kanban-board-manager/SKILL.md` et al. 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: `.opencode/skills/boomerang-handoff/SKILL.md`, `.opencode/skills/boomerang-orchestrator/SKILL.md`, `.opencode/skills/external-skills-fetcher/SKILL.md`, `.opencode/skills/kanban-board-manager/SKILL.md` et al. 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: `AGENTS.md`, `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, `clm_0007` supported 0.86 ### What You Cannot Trust Yet - **Research conclusions, citations, and experiment results cannot be trusted before install.** (unverified): A research Skill can organize questions and paths, but it cannot replace real literature search, paper verification, and experiment reproduction. - **Whether it fits your specific research field cannot be trusted directly.** (unverified): The Skill covering many research topics does not mean it is sufficient for your field, source requirements, and credibility standards. - **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: `.opencode/skills/boomerang-handoff/SKILL.md`, `.opencode/skills/boomerang-orchestrator/SKILL.md`, `.opencode/skills/external-skills-fetcher/SKILL.md`, `.opencode/skills/kanban-board-manager/SKILL.md` et al. - **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. ### What Continuing Will Touch - **Research judgment**: Problem decomposition, source paths, experiment paths, conclusion structure, and credibility judgment. Why: A research Skill can make output look more professional but cannot replace real evidence verification. - **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: `AGENTS.md`, `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: `.opencode/skills/boomerang-handoff/SKILL.md`, `.opencode/skills/boomerang-orchestrator/SKILL.md`, `.opencode/skills/external-skills-fetcher/SKILL.md`, `.opencode/skills/kanban-board-manager/SKILL.md` et al. - **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: `AGENTS.md`, `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: `docs/archive/v0-pre-docs/MIGRATION_GUIDE.md`, `docs/getting-started/quickstart.md`, `docs/reference/env-vars.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**: Verify whether it can correctly frame the research question and evidence boundaries first; do not trust the research output up front. (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. - **Keep a source and conclusion verification checklist**: If citations or experiment paths later prove unreliable, you can return to the evidence-boundary stage and re-check. - **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_0008` 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: `AGENTS.md`, `README.md` Claim: `clm_0009` 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: `.opencode/skills/boomerang-handoff/SKILL.md`, `.opencode/skills/boomerang-orchestrator/SKILL.md`, `.opencode/skills/external-skills-fetcher/SKILL.md`, `.opencode/skills/kanban-board-manager/SKILL.md` et al. 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: `AGENTS.md`, `README.md` Claim: `clm_0002` supported 0.86 ### Context Scale - Total files: 481 - Important-file coverage: 40/481 - Evidence index entries: 70 - Role / Skill entries: 7 ### 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 neuralgentics, 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 neuralgentics 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 neuralgentics, 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 7 role / Skill / project-doc entries. - **boomerang-handoff** (skill): End-of-session wrap-up. Runs the self-evolution gate auto-create , then updates HANDOFF.md + TASKS.md, then commits any new SKILL.md files. Invoke via //boomerang-handoff . Activation hint: When the user's task is highly relevant to the workflow described by “boomerang-handoff”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/boomerang-handoff/SKILL.md` - **boomerang-orchestrator** (skill): Main coordinator for Boomerang Cycle v3 kanban-native . Extrapolates the user prompt, dispatches the architect for a roadmap, seeds the kanban, dispatches narrow cards to workers broker permission-gated , and runs a wrap-up audit with skill self-audit and todo-list update. Activation hint: When the user's task is highly relevant to the workflow described by “boomerang-orchestrator”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/boomerang-orchestrator/SKILL.md` - **external-skills-fetcher** (skill): Clones the curated external skill repos Orchestra-Research/AI-Research-SKILLs + nextlevelbuilder/ui-ux-pro-max-skill into ~/.neuralgentics/external skills/. Refreshes on session start. Toggle via external skills.enabled in .env. Invoke via //external-skills-fetcher. Activation hint: When the user's task is highly relevant to the workflow described by “external-skills-fetcher”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/external-skills-fetcher/SKILL.md` - **kanban-board-manager** (skill): Manages the Boomerang kanban board in TASKS.md. Creates, moves, and audits cards across seven statuses triage, todo, ready, running, blocked, done, archived . Seeded by the orchestrator from a roadmap; queried by the orchestrator to find ready cards for dispatch; updated by workers when they complete a card. The board is the durable source of truth for "what is being worked on. Activation hint: When the user's task is highly relevant to the workflow described by “kanban-board-manager”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/kanban-board-manager/SKILL.md` - **skill-self-audit** (skill): End-of-cycle audit that detects repeated processes and creates skills for them. Invoked by the orchestrator before wrap-up. If a process was repeated more than once during the cycle, the orchestrator invokes boomerang-agent-builder to formalize it as a skill before signing off. Activation hint: When the user's task is highly relevant to the workflow described by “skill-self-audit”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/skill-self-audit/SKILL.md` - **todo-list-updater** (skill): Refreshes the project's todo list TASKS.md or its Current Phase section to reflect the current cycle's state. Invoked by the orchestrator at end of cycle, when a phase transitions, or when the user asks to clean up the todo list. Marks done items, removes stale items, adds newly discovered items, and keeps the file scannable for the next cycle. Activation hint: When the user's task is highly relevant to the workflow described by “todo-list-updater”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/todo-list-updater/SKILL.md` - **update-gh-docs** (skill): Updates GitHub-flavored documentation README, CHANGELOG, release notes so they are consistent, well-formatted, and validated to render correctly on github.com. Invoked as part of the release-card workflow, before tagging a release. Generic prompts for any GitHub-hosted project, with neuralgentics-specific tailoring hero copy from Session 22, fish-shell user, podman-only, no docker, repo at Veedubin/neuralgentics . Activation hint: When the user's task is highly relevant to the workflow described by “update-gh-docs”, use it for a pre-install experience first, then decide whether to install. Evidence: `.opencode/skills/update-gh-docs/SKILL.md` ## Evidence Index - Indexed 70 evidence entries. - **Neuralgentics Agents** (documentation): Provider Configuration Ollama Cloud & Alternatives Evidence: `AGENTS.md` - **Neuralgentics** (documentation): An open-source agent runtime, built for engineers who ship. Evidence: `README.md` - **@neuralgentics/plugin** (documentation): OpenCode integration plugin that wires the Neuralgentics runtime into the IDE. Evidence: `packages/plugin/README.md` - **@neuralgentics/sdk** (documentation): Typed client library for Neuralgentics sub-agents and external consumers. Evidence: `packages/sdk/README.md` - **@neuralgentics/tui** (documentation): OpenTUI-based terminal interface for Neuralgentics v0.1.0. Evidence: `packages/tui/README.md` - **Changelog** (documentation): All notable changes to this project will be documented in this file. Evidence: `docs/changelog.md` - **Troubleshooting** (documentation): This guide covers the most common errors encountered when running Neuralgentics. Evidence: `docs/troubleshooting.md` - **Broker Flow** (documentation): The Neuralgentics Broker is the strategic gatekeeper between the agent swarm and the external world. Its primary purpose is to enforce permissions and minimize token waste. Evidence: `docs/architecture/broker-flow.md` - **Dispatch Flow** (documentation): The Orchestrator is the "brain" of the session. It translates a vague user request into a deterministic set of tasks, ensuring no step is skipped and every agent has exactly the context it needs. Evidence: `docs/architecture/dispatch-flow.md` - **System Overview** (documentation): The Harness neuralgentics is the harness that turns a language model into a reliable agent. The harness consists of: the broker tool permission enforcement , the memory engine trust-scored persistence , the kanban work decomposition , and the protocol 8-step mandatory lifecycle . Evidence: `docs/architecture/overview.md` - **Permission Model** (documentation): Neuralgentics employs a rigid Role-Based Access Control RBAC model. This is not just for security; it is fundamentally about token optimization . By restricting the tool catalog available to a specific agent, we prevent "tool-drift" and reduce prompt noise. Evidence: `docs/architecture/permission-model.md` - **Installation** (documentation): You're installing the harness for AI agents - a 26 MB Go binary that brokers tool calls, scores memory, and persists context across sessions. Evidence: `docs/getting-started/installation.md` - **Quickstart** (documentation): Get Neuralgentics from "Clone" to "First Dispatch" in under 5 minutes. Evidence: `docs/getting-started/quickstart.md` - **Package** (package_manifest): { "dependencies": { "@opencode-ai/plugin": "1.15.9" } } Evidence: `.opencode/package.json` - **Package** (package_manifest): { "name": "@neuralgentics/root", "version": "0.9.0", "description": "Neuralgentics — coding agent built on OpenCode", "private": true, "type": "module", "bin": { "neuralgentics": "./neuralgentics" }, "scripts": { "start": "./neuralgentics start", "serve": "./neuralgentics serve", "build": "./scripts/build.sh", "build:ts": "tsc -p packages/plugin/tsconfig.json && tsc -p packages/orchestrator/tsconfig.json", "build:py": "cd packages/memini-core && uv build", "install:all": "bun install && cd packages/memini-core && uv sync", "dev:memini": "cd packages/memini-core && uv run python -m memini core.server", "dev:plugin": "bun run --watch packages/plugin/src/index.ts", "test": "bun test packages/p… Evidence: `package.json` - **Package** (package_manifest): { "name": "@veedubin/neuralgentics", "version": "0.9.2", "description": "Neuralgentics OpenCode plugin — agent personas, skills, routing enforcement, and MCP tools.", "type": "module", "main": "./dist/server.js", "types": "./dist/server.d.ts", "files": "dist/" , "exports": { ".": { "import": "./dist/server.js", "types": "./dist/server.d.ts" }, "./library": { "import": "./dist/neuralgentics/index.js", "types": "./dist/neuralgentics/index.d.ts" }, "./server": { "import": "./dist/server.js", "types": "./dist/server.d.ts" } }, "scripts": { "build": "tsc", "typecheck": "tsc --noEmit", "test:e2e": "node e2e test.mjs", "prepublishOnly": "npm run typecheck && npm run build" }, "keywords": "opencode… Evidence: `overlay/packages/opencode/package.json` - **Package** (package_manifest): { "name": "@neuralgentics/orchestrator", "version": "0.0.1-alpha", "description": "Neuralgentics orchestrator — routing, protocol enforcement, context building", "type": "module", "main": "dist/index.js", "types": "dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" }, "./types": { "import": "./dist/types.js", "types": "./dist/types.d.ts" } }, "scripts": { "build": "tsc", "typecheck": "tsc --noEmit", "test": "vitest run", "test:watch": "vitest" }, "dependencies": {}, "devDependencies": { "@types/node": "^22.0.0", "typescript": "^5.7.0", "vitest": "^3.0.0" }, "peerDependencies": {}, "engines": { "node": " =20.0.0" } } Evidence: `packages/orchestrator/package.json` - **Package** (package_manifest): { "name": "@neuralgentics/plugin", "version": "0.2.0", "description": "Neuralgentics OpenCode plugin — MCP tools, memory adapter, routing enforcement", "type": "module", "main": "dist/index.js", "types": "dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" }, "./adapters": { "import": "./dist/adapters/index.js", "types": "./dist/adapters/index.d.ts" } }, "scripts": { "build": "tsc", "typecheck": "tsc --noEmit" }, "dependencies": { "@neuralgentics/orchestrator": "workspace: " }, "devDependencies": { "@types/node": "^22.0.0", "typescript": "^5.7.0" }, "engines": { "node": " =20.0.0" } } Evidence: `packages/plugin/package.json` - **Package** (package_manifest): { "name": "@neuralgentics/sdk", "version": "0.2.0", "description": "Boomerang SDK wrapper — typed client, routing, memory adapter, and hook abstractions for Neuralgentics", "type": "module", "main": "dist/index.js", "types": "dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" }, "./types": { "import": "./dist/types.js", "types": "./dist/types.d.ts" }, "./adapters": { "import": "./dist/adapters/index.js", "types": "./dist/adapters/index.d.ts" } }, "scripts": { "build": "tsc", "typecheck": "tsc --noEmit", "test": "vitest run", "test:watch": "vitest" }, "dependencies": { "@neuralgentics/orchestrator": "workspace: " }, "peerDependencies": { "@opencod… Evidence: `packages/sdk/package.json` - **Package** (package_manifest): { "name": "@neuralgentics/tui", "version": "0.9.0", "description": "Neuralgentics TUI — OpenTUI-based terminal interface", "type": "module", "main": "src/index.ts", "module": "src/index.ts", "types": "src/index.ts", "scripts": { "start": "bun run src/index.ts", "build": "bun build src/index.ts --outdir=dist --target=bun", "lint": "eslint src/ --ext .ts", "typecheck": "tsc --noEmit", "test": "bun test" }, "dependencies": { "@opencode-ai/sdk": "^1.15.13", "@opentui/core": "^0.3.1", "@opentui/core-linux-x64": "^0.3.1" }, "devDependencies": { "@types/bun": "latest", "typescript": "^5" }, "engines": { "bun": " =1.3.0" } } Evidence: `packages/tui/package.json` - **Boomerang Handoff** (skill_instruction): At the end of every session , or when the user explicitly requests //boomerang-handoff . This skill wraps up the session, runs the self-evolution gate to auto-create skills from repeated patterns, updates documentation, and commits any new artifacts. Evidence: `.opencode/skills/boomerang-handoff/SKILL.md` - **Boomerang Orchestrator** (skill_instruction): At session start, if external skills.enabled=true in ~/.neuralgentics/.env , invoke the external-skills-fetcher skill to ensure the curated external skill repos are cloned and up-to-date. This is done BEFORE the SESSION START PROTOCOL so that the new SKILL.md files are visible to AGENTS.md and the rest of the protocol. Evidence: `.opencode/skills/boomerang-orchestrator/SKILL.md` - **External Skills Fetcher** (skill_instruction): - At session start — the plugin's session-start hook invokes this skill automatically before the SESSION START PROTOCOL so that the new SKILL.md files are visible to AGENTS.md and the rest of the protocol . - Manually — via //external-skills-fetcher when the user wants to refresh external skills mid-session. - At release time — scripts/release.sh calls the fetcher before building the dist tarball. Evidence: `.opencode/skills/external-skills-fetcher/SKILL.md` - **Kanban Board Manager** (skill_instruction): The kanban board lives in the project's TASKS.md file. It has seven statuses Hermes-compatible and supports dependency links between cards. The board manager is the only agent that mutates the board. Workers report status changes through it; the orchestrator queries it to find ready cards. Evidence: `.opencode/skills/kanban-board-manager/SKILL.md` - **Skill Self-Audit** (skill_instruction): The orchestrator runs this audit at the end of every cycle. The audit scans the cycle for processes that were repeated more than once — and if any are found, the orchestrator creates a skill for them. This is how the Boomerang v3 skill library grows organically: as patterns repeat, they get formalized. Evidence: `.opencode/skills/skill-self-audit/SKILL.md` - **Todo List Updater** (skill_instruction): The todo list lives in TASKS.md or in a project-specific location if the project overrides the convention . The orchestrator invokes this skill to keep the file current. The file is the canonical "what are we working on right now" — chat scrollback and memory are not. Evidence: `.opencode/skills/todo-list-updater/SKILL.md` - **Update GitHub Docs** (skill_instruction): When the orchestrator is about to tag a release, this skill updates the GitHub-visible documentation files README.md , CHANGELOG.md , GitHub release notes, and any repo-root .md files visitors see first so they are: - Consistent — version numbers, dates, links all match - Complete — every public-facing file has accurate content - Formatted correctly — renders cleanly on github.com no broken markdown, no mermaid — use Unicode box-drawing per neuralgentics house style - Validated — links resolve, code blocks have correct language tags, table-of-contents works Evidence: `.opencode/skills/update-gh-docs/SKILL.md` - **License** (source_file): Copyright c 2026 neuralgentics contributors Evidence: `LICENSE` - **C.1 — packages/core/ deletion v0.2.0 cleanup** (documentation): C.1 — packages/core/ deletion v0.2.0 cleanup Evidence: `docs/CLEANUP_C1_DELETE_CORE.md` - **C.3 — packages/broker/ Python deletion v0.2.0 cleanup** (documentation): C.3 — packages/broker/ Python deletion v0.2.0 cleanup Evidence: `docs/CLEANUP_C3_DELETE_PYTHON_BROKER.md` - **Development** (documentation): This guide is for contributors wishing to extend the Neuralgentics runtime. Evidence: `docs/development.md` - **Multi-Agent Orchestration, Permissions-based MCP Server Broker, Context Continuity Across Sessions** (documentation): Multi-Agent Orchestration, Permissions-based MCP Server Broker, Context Continuity Across Sessions Evidence: `docs/index.md` - **Python Embedding Sidecar Setup** (documentation): The Neuralgentics TUI can use a Python gRPC sidecar for BGE-Large 1024-dim embeddings. Without the sidecar, memory operations still work — they use noop 384-dim embeddings instead. The sidecar is an advanced feature for users who need high-quality semantic search. Evidence: `docs/sidecar-setup.md` - **Neuralgentics API Reference** (documentation): THIS DOCUMENT IS ARCHIVED AS OF 2026-06-04. It describes an older version of Neuralgentics and may reference APIs, install paths, or env vars that no longer exist. Evidence: `docs/archive/v0-pre-docs/API_REFERENCE.md` - **Architecture: Neuralgentics** (documentation): THIS DOCUMENT IS ARCHIVED AS OF 2026-06-04. It describes an older version of Neuralgentics and may reference APIs, install paths, or env vars that no longer exist. Evidence: `docs/archive/v0-pre-docs/ARCHITECTURE.md` - **Neuralgentics MCP Broker** (documentation): THIS DOCUMENT IS ARCHIVED AS OF 2026-06-04. It describes an older version of Neuralgentics and may reference APIs, install paths, or env vars that no longer exist. Evidence: `docs/archive/v0-pre-docs/BROKER.md` - **Neuralgentics Migration Guide** (documentation): THIS DOCUMENT IS ARCHIVED AS OF 2026-06-04. It describes an older version of Neuralgentics and may reference APIs, install paths, or env vars that no longer exist. Evidence: `docs/archive/v0-pre-docs/MIGRATION_GUIDE.md` - **Deferred Follow-ups** (documentation): Status: Parked ideas for future releases. None are blocking v0.5.0 current . They live here so they don't get lost across sessions. Evidence: `docs/design/deferred-followups.md` - **Neuralgentics Documentation Site — Design** (documentation): Neuralgentics Documentation Site — Design Evidence: `docs/design/docs-site-architecture.md` - **Neuralgentics Init CLI Bootstrapper — Architecture Design** (documentation): Neuralgentics Init CLI Bootstrapper — Architecture Design Evidence: `docs/design/init-cli-bootstrapper.md` - **Embedding Sidecar Productionization Design** (documentation): Embedding Sidecar Productionization Design Evidence: `docs/design/sidecar-productionization.md` - **Skills Brokering + Auto-Evolution — Phase 1 Design** (documentation): Skills Brokering + Auto-Evolution — Phase 1 Design Evidence: `docs/design/skills-brokering-phase-1-design.md` - **Skills Brokering + Auto-Evolution — Phase 2 Design** (documentation): Skills Brokering + Auto-Evolution — Phase 2 Design Evidence: `docs/design/skills-brokering-phase-2-design.md` - **Skills Brokering + Auto-Evolution — Phase 3 Design** (documentation): Skills Brokering + Auto-Evolution — Phase 3 Design Evidence: `docs/design/skills-brokering-phase-3-design.md` - **Transport Architecture & Multi-Provider Registry** (documentation): Transport Architecture & Multi-Provider Registry Evidence: `docs/design/transport-architecture.md` - **v0.5.0 Design: OCI-shareable Profile, HTTP/SSE Transport, small model Provider Awareness, CI -short Fix** (documentation): v0.5.0 Design: OCI-shareable Profile, HTTP/SSE Transport, small model Provider Awareness, CI -short Fix Evidence: `docs/design/v0.5.0-profile-and-transport.md` - **v0.6.0 — Tasks Table + Parking Lot in Postgres** (documentation): v0.6.0 — Tasks Table + Parking Lot in Postgres Evidence: `docs/design/v0.6.0-tasks-table-parked.md` - **Environment Variables** (documentation): Neuralgentics uses a multi-layered environment configuration to allow seamless transition from local development to production clouds. Evidence: `docs/reference/env-vars.md` - **Kanban System** (documentation): Neuralgentics manages work using a durable Kanban board located in TASKS.md . This prevents the "forgetting" problem common in long LLM sessions by anchoring progress in a physical file. Evidence: `docs/reference/kanban-system.md` - **Memory System** (documentation): Neuralgentics does not use a simple "vector search" for context. It implements a Trust-Weighted Semantic Memory system that separates raw data from verified patterns. Evidence: `docs/reference/memory-system.md` - **Session Lifecycle** (documentation): A Neuralgentics session is not a stream of chat messages; it is a strict sequence of states. Every single task MUST follow the 9-Step Mandatory Protocol . Evidence: `docs/reference/session-lifecycle.md` - **compose.example.env — Example environment for docker-compose / podman-compose** (source_file): compose.example.env — Example environment for docker-compose / podman-compose Usage: cp compose.example.env .env $EDITOR .env docker compose up or podman-compose up Evidence: `compose.example.env` - **Docker Compose** (source_file): version: "3.9" services: neuralgentics-postgres: image: ghcr.io/veedubin/neuralgentics-postgres:${NEURALGENTICS VERSION:-latest} build: context: . dockerfile: docker/postgres.Dockerfile container name: neuralgentics-postgres ports: - "${NEURALGENTICS DB PORT:-6000}:5432" environment: POSTGRES USER: ${NEURALGENTICS DB USER:-postgres} POSTGRES PASSWORD: ${NEURALGENTICS DB PASSWORD:-neuralgentics} POSTGRES DB: ${NEURALGENTICS DB NAME:-neuralgentics} volumes: - neuralgentics-db:/var/lib/postgresql/data networks: - neuralgentics-net healthcheck: test: "CMD-SHELL", "pg isready -U ${NEURALGENTICS DB USER:-postgres} -d ${NEURALGENTICS DB NAME:-neuralgentics}" interval: 5s timeout: 3s retries: 10 st… Evidence: `docker-compose.yml` - **docker/backend.Dockerfile** (source_file): docker/backend.Dockerfile Neuralgentics Go backend — multi-stage build. Produces a minimal static binary in a distroless final image. Evidence: `docker/backend.Dockerfile` - **docker/postgres.Dockerfile** (source_file): docker/postgres.Dockerfile PostgreSQL 18 + pgvector + TimescaleDB for Neuralgentics memory backend. pgvector/pgvector:pg18 already includes pgvector. We add TimescaleDB on top for time-series memory analytics trust decay, audit logs, session metrics . FROM pgvector/pgvector:pg18 Evidence: `docker/postgres.Dockerfile` - **docker/sidecar.Dockerfile** (source_file): docker/sidecar.Dockerfile Python gRPC embedding service for Neuralgentics. Multi-stage: builder installs deps, final image is slim. FROM python:3.11-slim-bookworm AS builder Evidence: `docker/sidecar.Dockerfile` - **Podman Compose** (source_file): version: "3.9" services: neuralgentics-postgres: image: ghcr.io/veedubin/neuralgentics-postgres:${NEURALGENTICS VERSION:-v0.2.0} build: context: . dockerfile: docker/postgres.Dockerfile container name: neuralgentics-postgres ports: - "${NEURALGENTICS DB PORT:-6000}:5432" environment: POSTGRES USER: ${NEURALGENTICS DB USER:-postgres} POSTGRES PASSWORD: ${NEURALGENTICS DB PASSWORD:-neuralgentics} POSTGRES DB: ${NEURALGENTICS DB NAME:-neuralgentics} volumes: - neuralgentics-db:/var/lib/postgresql/data:Z networks: - neuralgentics-net userns mode: "keep-id" pids limit: 1000 healthcheck: test: "CMD-SHELL", "pg isready -U ${NEURALGENTICS DB USER:-postgres} -d ${NEURALGENTICS DB NAME:-neuralgentics… Evidence: `podman-compose.yml` - **─────────────────────────────────────────────────────────────────────────────** (source_file): ───────────────────────────────────────────────────────────────────────────── Sample .env for neuralgentics — used by bash install.sh --existing to skip auto-creating a PostgreSQL container. Drop this at: $PWD/.neuralgentics/.env or wherever your NEURALGENTICS DATA DIR is — see install.sh --help . Required keys all 5 must be present, no defaults : POSTGRES HOST — hostname or IP of your PostgreSQL server POSTGRES PORT — port default 6000 for the auto-created container, 5432 for a stock postgres install POSTGRES USER — database role POSTGRES PASSWORD — role password POSTGRES DB — database name The install will refuse to proceed with --existing if any of these are missing or commented out. ───… Evidence: `scripts/.env.example` - **─── Logging ─────────────────────────────────────────────────────────────────** (source_file): set -euo pipefail APP="neuralgentics" DEFAULT VERSION="0.9.0" REPO="${NEURALGENTICS REPO:-Veedubin/neuralgentics}" PREFIX="" VERSION="${DEFAULT VERSION}" DRY RUN=false INSTALL HOME=false YES=false ─── Logging ───────────────────────────────────────────────────────────────── log { printf " %s %s\n" "$APP" "$ " &2; } warn { printf " warn %s\n" "$ " &2; } err { printf " ERROR %s\n" "$ " &2; exit 1; } has systemd { -d "$HOME/.config/systemd/user" && command -v systemctl /dev/null 2 &1 } install env file { local env file="$HOME/.neuralgentics/.env" if -f "$env file" ; then log "env file already exists at ${env file}, skipping" return 0 fi if $DRY RUN; then log " dry-run Would create ${env file}"… Evidence: `scripts/install.sh` - **Main** (source_file): package main ⋮---- import "fmt" "log" "neuralgentics-broker/src/neuralgentics/broker" "neuralgentics-broker/src/neuralgentics/broker/access" "neuralgentics-broker/src/neuralgentics/broker/types" ⋮---- "fmt" "log" ⋮---- "neuralgentics-broker/src/neuralgentics/broker" "neuralgentics-broker/src/neuralgentics/broker/access" "neuralgentics-broker/src/neuralgentics/broker/types" ⋮---- func main ⋮---- var serverTools types.ToolSummary Evidence: `packages/broker-go/cmd/broker/main.go` - The remaining 10 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: `AGENTS.md`, `README.md`, `packages/plugin/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: `AGENTS.md`, `README.md`, `packages/plugin/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, Agent Personas & Installation**: importance `high` - source_paths: README.md, AGENTS.md, scripts/install.sh, scripts/.env.example, docs/getting-started/installation.md - **System Architecture: Orchestrator, Broker & Dispatch Flow**: importance `high` - source_paths: docs/architecture/overview.md, docs/architecture/broker-flow.md, docs/architecture/dispatch-flow.md, docs/architecture/permission-model.md, packages/backend-go/cmd/backend/main.go - **Core Features: Memory Engine, Skills Brokering, Kanban & Stateless Protocol**: importance `high` - source_paths: packages/memory/src/neuralgentics/memory/memory.go, packages/memory/src/neuralgentics/memory/core/types.go, packages/memory/src/neuralgentics/memory/store/postgres.go, packages/memory/src/neuralgentics/memory/store/memories.go, packages/memory/src/neuralgentics/memory/store/memories_1024.go - **Deployment, Sidecar Lifecycle & Troubleshooting**: importance `medium` - source_paths: docker-compose.yml, podman-compose.yml, compose.example.env, docker/backend.Dockerfile, docker/postgres.Dockerfile ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `9b7723bd8ed0e9b6121bc18989a62b0b4ce06383` - inspected_files: `README.md`, `docker-compose.yml`, `package.json`, `pyproject.toml`, `docs/CLEANUP_C1_DELETE_CORE.md`, `docs/CLEANUP_C3_DELETE_PYTHON_BROKER.md`, `docs/architecture/broker-flow.md`, `docs/architecture/diagrams/combined/mermaid-config.json`, `docs/architecture/diagrams/combined/puppeteer.json`, `docs/architecture/diagrams/mermaid-config.json`, `docs/architecture/diagrams/puppeteer.json`, `docs/architecture/dispatch-flow.md`, `docs/architecture/overview.md`, `docs/architecture/permission-model.md`, `docs/archive/v0-pre-docs/API_REFERENCE.md`, `docs/archive/v0-pre-docs/ARCHITECTURE.md`, `docs/archive/v0-pre-docs/BROKER.md`, `docs/archive/v0-pre-docs/MIGRATION_GUIDE.md`, `docs/changelog.md`, `docs/design/deferred-followups.md` 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: Neuralgentics v0.6.7 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Neuralgentics v0.6.7. Context: Observed when using python, docker - Why it matters: Upgrade or migration may change expected behavior: Neuralgentics v0.6.7 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.6.7 - 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: Neuralgentics v0.6.8 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Neuralgentics v0.6.8. Context: Observed when using python, docker - Why it matters: Upgrade or migration may change expected behavior: Neuralgentics v0.6.8 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.6.8 - 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: Neuralgentics v0.7.0 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Neuralgentics v0.7.0. Context: Observed when using python, docker - Why it matters: Upgrade or migration may change expected behavior: Neuralgentics v0.7.0 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.7.0 - 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: Neuralgentics v0.7.1 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Neuralgentics v0.7.1. Context: Observed when using python, docker - Why it matters: Upgrade or migration may change expected behavior: Neuralgentics v0.7.1 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.7.1 - 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: neuralgentics-0.7.2 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: neuralgentics-0.7.2. Context: Observed during installation or first-run setup. - Why it matters: Upgrade or migration may change expected behavior: neuralgentics-0.7.2 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.7.2 - 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: neuralgentics-0.7.3 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: neuralgentics-0.7.3. Context: Observed during installation or first-run setup. - Why it matters: Upgrade or migration may change expected behavior: neuralgentics-0.7.3 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.7.3 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 7: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: neuralgentics-0.8.0 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: neuralgentics-0.8.0. Context: Observed during installation or first-run setup. - Why it matters: Upgrade or migration may change expected behavior: neuralgentics-0.8.0 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.8.0 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 8: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: neuralgentics-0.9.0 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: neuralgentics-0.9.0. Context: Observed during installation or first-run setup. - Why it matters: Upgrade or migration may change expected behavior: neuralgentics-0.9.0 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.9.0 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 9: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: neuralgentics-0.9.1 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: neuralgentics-0.9.1. Context: Observed when using node - Why it matters: Upgrade or migration may change expected behavior: neuralgentics-0.9.1 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.9.1 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 10: Installation risk requires verification - Trigger: Developers should check this installation risk before relying on the project: neuralgentics-0.9.2 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: neuralgentics-0.9.2. Context: Observed when using node - Why it matters: Upgrade or migration may change expected behavior: neuralgentics-0.9.2 - Evidence: failure_mode_cluster:github_release | https://github.com/Veedubin/neuralgentics/releases/tag/v0.9.2 - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.