@bohuyeshan/openagent-labforge-core 3.11.2 → 3.11.4

package/README.md

@@ -1,9 +1,15 @@
-> [!NOTE]
-> **Derivative Notice**
-> 
-> This project is a fork/derivative of `code-yeongyu/oh-my-openagent` (formerly `oh-my-opencode`).
-> We have renamed the project and added new features and configuration options focused on user-controlled model routing and research workflows.
-> Licensing and provenance are documented in `LICENSE.md`, `NOTICE`, `THIRD_PARTY_NOTICES.md`, and `docs/licensing.md`.
+> [!WARNING]
+> **TEMP NOTICE (This Week): Reduced Maintainer Availability**
+>
+> Core maintainer Q got injured, so issue/PR responses and releases may be delayed this week.
+> Thank you for your patience and support.
+
+> [!NOTE]
+> **Derivative Notice**
+> 
+> This project is a fork/derivative of `code-yeongyu/openagent-labforge` (formerly `openagent-labforge`).
+> We have renamed the project and added new features and configuration options focused on user-controlled model routing and research workflows.
+> Licensing and provenance are documented in `LICENSE.md`, `NOTICE`, `THIRD_PARTY_NOTICES.md`, and `docs/licensing.md`.
 >
 > [![Sisyphus Labs - Sisyphus is the agent that codes like your team.](./.github/assets/sisyphuslabs.png?v=2)](https://sisyphuslabs.ai)
 > > **We're building a fully productized version of Sisyphus to define the future of frontier agents. <br />Join the waitlist [here](https://sisyphuslabs.ai).**
@@ -11,18 +17,18 @@
 > [!TIP]
 > Be with us!
 >
-> | [<img alt="Discord link" src="https://img.shields.io/discord/1452487457085063218?color=5865F2&label=discord&labelColor=black&logo=discord&logoColor=white&style=flat-square" width="156px" />](https://discord.gg/PUwSMR9XNk) | Join our [Discord community](https://discord.gg/PUwSMR9XNk) to connect with contributors and fellow `oh-my-opencode` users. |
+> | [<img alt="Discord link" src="https://img.shields.io/discord/1452487457085063218?color=5865F2&label=discord&labelColor=black&logo=discord&logoColor=white&style=flat-square" width="156px" />](https://discord.gg/PUwSMR9XNk) | Join our [Discord community](https://discord.gg/PUwSMR9XNk) to connect with contributors and fellow `openagent-labforge` users. |
 > | :-----| :----- |
-> | [<img alt="X link" src="https://img.shields.io/badge/Follow-%40justsisyphus-00CED1?style=flat-square&logo=x&labelColor=black" width="156px" />](https://x.com/justsisyphus) | News and updates for `oh-my-opencode` used to be posted on my X account. <br /> Since it was suspended mistakenly, [@justsisyphus](https://x.com/justsisyphus) now posts updates on my behalf. |
+> | [<img alt="X link" src="https://img.shields.io/badge/Follow-%40justsisyphus-00CED1?style=flat-square&logo=x&labelColor=black" width="156px" />](https://x.com/justsisyphus) | News and updates for `openagent-labforge` used to be posted on my X account. <br /> Since it was suspended mistakenly, [@justsisyphus](https://x.com/justsisyphus) now posts updates on my behalf. |
 > | [<img alt="GitHub Follow" src="https://img.shields.io/github/followers/code-yeongyu?style=flat-square&logo=github&labelColor=black&color=24292f" width="156px" />](https://github.com/code-yeongyu) | Follow [@code-yeongyu](https://github.com/code-yeongyu) on GitHub for more projects. |
 
 <!-- <CENTERED SECTION FOR GITHUB DISPLAY> -->
 
 <div align="center">
 
-[![Oh My OpenCode](./.github/assets/hero.jpg)](https://github.com/code-yeongyu/oh-my-opencode#oh-my-opencode)
+[![OpenAgent Labforge](./.github/assets/hero.jpg)](https://github.com/code-yeongyu/openagent-labforge#openagent-labforge)
 
-[![Preview](./.github/assets/omo.png)](https://github.com/code-yeongyu/oh-my-opencode#oh-my-opencode)
+[![Preview](./.github/assets/omo.png)](https://github.com/code-yeongyu/openagent-labforge#openagent-labforge)
 
 
 </div>
@@ -35,14 +41,14 @@
 
 <div align="center">
 
-[![GitHub Release](https://img.shields.io/github/v/release/code-yeongyu/oh-my-opencode?color=369eff&labelColor=black&logo=github&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/releases)
-[![npm downloads](https://img.shields.io/npm/dt/oh-my-opencode?color=ff6b35&labelColor=black&style=flat-square)](https://www.npmjs.com/package/oh-my-opencode)
-[![GitHub Contributors](https://img.shields.io/github/contributors/code-yeongyu/oh-my-opencode?color=c4f042&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/graphs/contributors)
-[![GitHub Forks](https://img.shields.io/github/forks/code-yeongyu/oh-my-opencode?color=8ae8ff&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/network/members)
-[![GitHub Stars](https://img.shields.io/github/stars/code-yeongyu/oh-my-opencode?color=ffcb47&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/stargazers)
-[![GitHub Issues](https://img.shields.io/github/issues/code-yeongyu/oh-my-opencode?color=ff80eb&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/issues)
-[![License](https://img.shields.io/badge/license-SUL--1.0-white?labelColor=black&style=flat-square)](https://github.com/code-yeongyu/oh-my-opencode/blob/dev/LICENSE.md)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/code-yeongyu/oh-my-opencode)
+[![GitHub Release](https://img.shields.io/github/v/release/code-yeongyu/openagent-labforge?color=369eff&labelColor=black&logo=github&style=flat-square)](https://github.com/code-yeongyu/openagent-labforge/releases)
+[![npm downloads](https://img.shields.io/endpoint?url=https%3A%2F%2Fohmyopenagent.com%2Fapi%2Fnpm-downloads&style=flat-square)](https://www.npmjs.com/package/openagent-labforge)
+[![GitHub Contributors](https://img.shields.io/github/contributors/code-yeongyu/openagent-labforge?color=c4f042&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/openagent-labforge/graphs/contributors)
+[![GitHub Forks](https://img.shields.io/github/forks/code-yeongyu/openagent-labforge?color=8ae8ff&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/openagent-labforge/network/members)
+[![GitHub Stars](https://img.shields.io/github/stars/code-yeongyu/openagent-labforge?color=ffcb47&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/openagent-labforge/stargazers)
+[![GitHub Issues](https://img.shields.io/github/issues/code-yeongyu/openagent-labforge?color=ff80eb&labelColor=black&style=flat-square)](https://github.com/code-yeongyu/openagent-labforge/issues)
+[![License](https://img.shields.io/badge/license-SUL--1.0-white?labelColor=black&style=flat-square)](https://github.com/code-yeongyu/openagent-labforge/blob/dev/LICENSE.md)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/code-yeongyu/openagent-labforge)
 
 [English](README.md) | [한국어](README.ko.md) | [日本語](README.ja.md) | [简体中文](README.zh-cn.md)
 
@@ -56,169 +62,219 @@
 
 > "If Claude Code does in 7 days what a human does in 3 months, Sisyphus does it in 1 hour. It just works until the task is done. It is a discipline agent." <br/>- B, Quant Researcher
 
-> "Knocked out 8000 eslint warnings with Oh My Opencode, just in a day" <br/>- [Jacob Ferrari](https://x.com/jacobferrari_/status/2003258761952289061)
+> "Knocked out 8000 eslint warnings with OpenAgent Labforge, just in a day" <br/>- [Jacob Ferrari](https://x.com/jacobferrari_/status/2003258761952289061)
 
 > "I converted a 45k line tauri app into a SaaS web app overnight using Ohmyopencode and ralph loop. Started with interview me prompt, asked it for ratings and recommendations on the questions. It was amazing to watch it work and to wake up this morning to a mostly working website!" - [James Hargis](https://x.com/hargabyte/status/2007299688261882202)
 
-> "use oh-my-opencode, you will never go back" <br/>- [d0t3ch](https://x.com/d0t3ch/status/2001685618200580503)
+> "use openagent-labforge, you will never go back" <br/>- [d0t3ch](https://x.com/d0t3ch/status/2001685618200580503)
 
 > "I haven't really been able to articulate exactly what makes it so great yet, but the development experience has reached a completely different dimension." - [
 苔硯:こけすずり](https://x.com/kokesuzuri/status/2008532913961529372?s=20)
 
-> "Experimenting with open code, oh my opencode and supermemory this weekend to build some minecraft/souls-like abomination."
+> "Experimenting with open code, OpenAgent Labforge and supermemory this weekend to build some minecraft/souls-like abomination."
 > "Asking it to add crouch animations while I go take my post-lunch walk. [Video]" - [MagiMetal](https://x.com/MagiMetal/status/2005374704178373023)
 
 > "You guys should pull this into core and recruit him. Seriously. It's really, really, really good." <br/>- Henning Kilset
 
 > "Hire @yeon_gyu_kim if you can convince him, this dude has revolutionized opencode." <br/>- [mysticaltech](https://x.com/mysticaltech/status/2001858758608376079)
 
-> "Oh My OpenCode Is Actually Insane" - [YouTube - Darren Builds AI](https://www.youtube.com/watch?v=G_Snfh2M41M)
+> "OpenAgent Labforge Is Actually Insane" - [YouTube - Darren Builds AI](https://www.youtube.com/watch?v=G_Snfh2M41M)
 
 ---
 
-# Oh My OpenCode
+# OpenAgent Labforge
 
 You're juggling Claude Code, Codex, random OSS models. Configuring workflows. Debugging agents.
 
 We did the work. Tested everything. Kept what actually shipped.
 
-Install OmO. Type `ultrawork`. Done.
-
-## Change Summary (Labforge)
-
-- Renamed fork with a derivative notice and third-party provenance.
-- Restored lightweight default plan and build behavior with explicit toggles.
-- Added Model Governor AUTO for discovery, category defaults, and fallback chains.
-- Enforced manual model selection priority to prevent unwanted overrides.
-- Added i18n agent display names and SOUL rule injection controls.
-- Added built-in skills for DOCX, PDF, PPTX, XLSX, web research, and data analysis.
-- Added research-oriented MCP defaults, explicit MCP policy, and visible default-off research MCPs.
-- Added unified `full` / `paper` skills bundles with source-aware naming and bundle loading.
-- Reduced skill initialization overhead with metadata-first preview and lazy merged-skill access.
-- Hardened todo continuation behavior to better respect user-facing question/confirmation flows.
-
-## Research-Focused Design
-
-- This derivative keeps the original programming strengths and adds research-oriented defaults directly in core.
-- Core now includes model governance, SOUL injection controls, and document/research skill presets.
-- Skills now support a unified functional catalog with metadata-first preview and lazy body loading.
-- Curated skills are split into `paper` and `full` bundles for lower token overhead at runtime.
-- Companion plugins are still recommended for domain depth:
-  - `opencode-agent-bio-paper`
-  - `opencode-mcp-paper-search`
-- See `plugins/BUNDLES.md` for `full` and `paper-only` bundle profiles.
-
-## Unified Skills Catalog
-
-- Generate the curated functional catalog:
-
-```bash
-bun run build:skills-catalog
-```
-
-- Use the runtime bundle shortcut:
-
-```jsonc
-{
-  "skills": {
-    "bundle": "full"
-  }
-}
-```
-
-or:
-
-```jsonc
-{
-  "skills": {
-    "bundle": "paper"
-  }
-}
-```
-
-- Generated outputs:
-  - `generated/skills-bundles/catalog.json`
-  - `generated/skills-bundles/full/INDEX.md`
-  - `generated/skills-bundles/paper/INDEX.md`
-
-The model now previews skill `name`, `description`, and `category` first, then reads full skill instructions only when needed.
-
-To avoid collisions between curated sources, external bundle skills use source-prefixed IDs (for example `openai-curated/openai-docs`, `anthropic/mcp-builder`), while builtin skills keep their original stable names.
-
-## Model Selection Guarantee
-
-- User-selected model is treated as highest priority across build/plan and all added agents.
-- AUTO is explicit (`auto` provider entry) and does not override explicit model pinning.
-- Strict lock is enabled by default and configurable:
-
-```jsonc
-{
-  "experimental": {
-    "strict_user_model_priority": true
-  }
-}
-```
+Install OmO. Type `ultrawork`. Done.
+
+## Change Summary (Labforge)
+
+- Renamed fork with a derivative notice and third-party provenance.
+- Restored lightweight default plan and build behavior with explicit toggles.
+- Added Model Governor AUTO for discovery, category defaults, and fallback chains.
+- Enforced manual model selection priority to prevent unwanted overrides.
+- Added i18n agent display names and SOUL rule injection controls.
+- Added built-in skills for DOCX, PDF, PPTX, XLSX, web research, and data analysis.
+- Added research-oriented MCP defaults, explicit MCP policy, and visible default-off research MCPs.
+- Added unified `full` / `paper` skills bundles with source-aware naming and bundle loading.
+- Reduced skill initialization overhead with metadata-first preview and lazy merged-skill access.
+- Hardened todo continuation behavior to better respect user-facing question/confirmation flows.
+
+## Research-Focused Design
+
+- This derivative keeps the original programming strengths and adds research-oriented defaults directly in core.
+- Core now includes model governance, SOUL injection controls, and document/research skill presets.
+- Skills now support a unified functional catalog with metadata-first preview and lazy body loading.
+- Curated skills are split into `paper` and `full` bundles for lower token overhead at runtime.
+- Companion plugins are still recommended for domain depth:
+  - `opencode-agent-bio-paper`
+  - `opencode-mcp-paper-search`
+- See `plugins/BUNDLES.md` for `full` and `paper-only` bundle profiles.
+
+## Unified Skills Catalog
+
+- Generate the curated functional catalog:
+
+```bash
+bun run build:skills-catalog
+```
+
+- Use the runtime bundle shortcut:
+
+```jsonc
+{
+  "skills": {
+    "bundle": "full"
+  }
+}
+```
+
+or:
+
+```jsonc
+{
+  "skills": {
+    "bundle": "paper"
+  }
+}
+```
+
+- Generated outputs:
+  - `generated/skills-bundles/catalog.json`
+  - `generated/skills-bundles/full/INDEX.md`
+  - `generated/skills-bundles/paper/INDEX.md`
+
+The model now previews skill `name`, `description`, and `category` first, then reads full skill instructions only when needed.
+
+To avoid collisions between curated sources, external bundle skills use source-prefixed IDs (for example `openai-curated/openai-docs`, `anthropic/mcp-builder`), while builtin skills keep their original stable names.
+
+## Model Selection Guarantee
+
+- User-selected model is treated as highest priority across build/plan and all added agents.
+- AUTO is explicit (`auto` provider entry) and does not override explicit model pinning.
+- Strict lock is enabled by default and configurable:
+
+```jsonc
+{
+  "experimental": {
+    "strict_user_model_priority": true
+  }
+}
+```
 
 
 ## Installation
 
-### Release Naming (Labforge)
-
-- Core package: `@labforge/openagent-labforge-core`
-- Full bundle target: `@labforge/openagent-labforge`
-- Paper-focused bundle target: `@labforge/openagent-labforge-paper`
-
-## Current Distribution Policy
-
-- Current recommended usage: **local build + local install**
-- Formal npm release is intentionally deferred for now
-- Upstream publish workflow differences are tracked in `docs/release/upstream-publish-notes.md`
-
-## Recommended Current Usage
-
-1. Build locally:
-
-```bash
-bun run build:skills-catalog
-bun run build
-```
-
-2. Install or load the local build into your OpenCode config directory.
-3. Use the bundle shortcut in plugin config:
-
-```jsonc
-{
-  "skills": {
-    "bundle": "full"
-  }
-}
-```
-
-4. Use `paper` if you want a smaller research-focused runtime surface.
-
-## Current Runtime Behavior
-
-- User-selected model remains highest priority across sessions and agents.
-- `skills.bundle = "full"` currently loads the complete curated bundle (builtin + curated external skills).
-- External bundle skills use source-prefixed IDs (for example `openai-curated/openai-docs`) to avoid collision with builtin skills.
-- Todo continuation is now more conservative:
-  - waits for a second idle cycle before injecting continuation
-  - respects `question` tool usage and common textual “waiting for user” patterns
-  - avoids immediate repeated continuation reinjection
-
-## Current Known Limits
-
-- Multi-window / multi-repository switching still depends partly on OpenCode host-side initialization behavior.
-- The plugin now avoids several repeated scans, but `createSkillContext` and host-side session loading can still add noticeable cold-start cost in very large workspaces or long-running OpenCode installations.
-- Formal npm publishing is intentionally deferred; local build + local install is the supported path for now.
-
-### For Humans
+### Published Package
+
+- Core package: `@bohuyeshan/openagent-labforge-core`
+- Current published version line: `3.11.x`
+- Legacy `@labforge/...` references remain in some historical docs and migration notes only
+
+## Current Distribution Policy
+
+- Current recommended usage: **npm install from the published package**
+- Local build + local install remains available for development and debugging
+- Upstream publish workflow differences are tracked in `docs/release/upstream-publish-notes.md`
+
+## Recommended Current Usage
+
+1. Install from npm:
+
+```bash
+npm install --prefix ~/.config/opencode @bohuyeshan/openagent-labforge-core@latest
+```
+
+2. Register the plugin in `opencode.json`:
+
+```jsonc
+{
+  "plugin": ["@bohuyeshan/openagent-labforge-core"]
+}
+```
+
+3. Use the bundle shortcut in plugin config:
+
+```bash
+bun run build:skills-catalog
+bun run build
+```
+
+```jsonc
+{
+  "skills": {
+    "bundle": "full"
+  }
+}
+```
+
+4. Use `paper` if you want a smaller research-focused runtime surface.
+
+5. Local development path (optional):
+
+```bash
+bun run build:skills-catalog
+bun run build
+npm pack
+npm install --prefix ~/.config/opencode /absolute/path/to/openagent-labforge-core-<version>.tgz
+```
+
+## Current Runtime Behavior
+
+- User-selected model remains highest priority across sessions and agents.
+- OpenAI-compatible providers such as `gmn` should keep a single GPT model entry (for example `gmn/gpt-5.3-codex`) and let the OpenCode UI control reasoning depth.
+- `skills.bundle = "full"` currently loads the complete curated bundle (builtin + curated external skills).
+- External bundle skills use source-prefixed IDs (for example `openai-curated/openai-docs`) to avoid collision with builtin skills.
+- Todo continuation is now more conservative:
+  - waits for a second idle cycle before injecting continuation
+  - respects `question` tool usage and common textual “waiting for user” patterns
+  - avoids immediate repeated continuation reinjection
+
+## Current Known Limits
+
+- Multi-window / multi-repository switching still depends partly on OpenCode host-side initialization behavior.
+- The plugin now avoids several repeated scans, but `createSkillContext` and host-side session loading can still add noticeable cold-start cost in very large workspaces or long-running OpenCode installations.
+- Large OpenCode host storage, stale session state, and very large workspaces can still make session hydration feel slower than raw startup.
+
+## Provider Note
+
+For OpenAI-compatible providers such as `gmn`, prefer a config shape like:
+
+```jsonc
+{
+  "provider": {
+    "gmn": {
+      "npm": "@ai-sdk/openai",
+      "options": {
+        "baseURL": "https://gmn.chuangzuoli.com/v1"
+      },
+      "models": {
+        "gpt-5.3-codex": {
+          "name": "GPT-5.3 Codex",
+          "limit": {
+            "context": 400000,
+            "output": 128000
+          }
+        }
+      }
+    }
+  },
+  "model": "gmn/gpt-5.3-codex"
+}
+```
+
+Keep reasoning depth in the OpenCode UI instead of hardcoding separate `low` / `medium` / `high` model aliases.
+
+### For Humans
 
 Copy and paste this prompt to your LLM agent (Claude Code, AmpCode, Cursor, etc.):
 
 ```
-Install and configure @labforge/openagent-labforge-core by following the instructions here:
-https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/refs/heads/dev/docs/guide/installation.md
+Install and configure @bohuyeshan/openagent-labforge-core by following the instructions here:
+https://raw.githubusercontent.com/code-yeongyu/openagent-labforge/refs/heads/dev/docs/guide/installation.md
 ```
 
 Or read the [Installation Guide](docs/guide/installation.md), but seriously, let an agent do it. Humans fat-finger configs.
@@ -228,7 +284,7 @@ Or read the [Installation Guide](docs/guide/installation.md), but seriously, let
 Fetch the installation guide and follow it:
 
 ```bash
-curl -s https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/refs/heads/dev/docs/guide/installation.md
+curl -s https://raw.githubusercontent.com/code-yeongyu/openagent-labforge/refs/heads/dev/docs/guide/installation.md
 ```
 
 ---
@@ -238,7 +294,7 @@ curl -s https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/refs/heads
 We're past the era of reading docs. Just paste this into your agent:
 
 ```
-Read this and tell me why it's not just another boilerplate: https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/refs/heads/dev/README.md
+Read this and tell me why it's not just another boilerplate: https://raw.githubusercontent.com/code-yeongyu/openagent-labforge/refs/heads/dev/README.md
 ```
 
 ## Highlights
@@ -294,7 +350,7 @@ Every agent is tuned to its model's specific strengths. No manual model-juggling
 >
 > We run best on Opus, but Kimi K2.5 + GPT-5.3 Codex already beats vanilla Claude Code. Zero config needed.
 
-### Agent Orchestration
+### Agent Orchestration
 
 When Sisyphus delegates to a subagent, it doesn't pick a model. It picks a **category**. The category maps automatically to the right model:
 
@@ -305,29 +361,29 @@ When Sisyphus delegates to a subagent, it doesn't pick a model. It picks a **cat
 | `quick`              | Single-file changes, typos         |
 | `ultrabrain`         | Hard logic, architecture decisions |
 
-Agent says what kind of work. Harness picks the right model. You touch nothing.
-
-### Model Governor (AUTO)
-
-AUTO detects available models, assigns category defaults, and builds fallback chains.
-It never overwrites your explicit config or UI-selected model.
-
-Config example:
-
-```jsonc
-{
-  "model_governor": {
-    "enabled": true,
-    "mode": "auto",
-    "report": { "enabled": true, "format": "md" }
-  }
-}
-```
-
-Reports and rules are written to your OpenCode config dir:
-
-- `openagent-labforge.models.report.md`
-- `openagent-labforge.models.rules.jsonc`
+Agent says what kind of work. Harness picks the right model. `ultrabrain` now routes to GPT-5.4 xhigh by default. You touch nothing.
+
+### Model Governor (AUTO)
+
+AUTO detects available models, assigns category defaults, and builds fallback chains.
+It never overwrites your explicit config or UI-selected model.
+
+Config example:
+
+```jsonc
+{
+  "model_governor": {
+    "enabled": true,
+    "mode": "auto",
+    "report": { "enabled": true, "format": "md" }
+  }
+}
+```
+
+Reports and rules are written to your OpenCode config dir:
+
+- `openagent-labforge.models.report.md`
+- `openagent-labforge.models.rules.jsonc`
 
 ### Claude Code Compatibility
 
@@ -407,19 +463,19 @@ Add your own: `.opencode/skills/*/SKILL.md` or `~/.config/opencode/skills/*/SKIL
 
 ---
 
-> **New to oh-my-opencode?** Read the **[Overview](docs/guide/overview.md)** to understand what you have, or check the **[Orchestration Guide](docs/guide/orchestration.md)** for how agents collaborate.
+> **New to openagent-labforge?** Read the **[Overview](docs/guide/overview.md)** to understand what you have, or check the **[Orchestration Guide](docs/guide/orchestration.md)** for how agents collaborate.
 
 ## Uninstallation
 
-To remove oh-my-opencode:
+To remove openagent-labforge:
 
 1. **Remove the plugin from your OpenCode config**
 
-   Edit `~/.config/opencode/opencode.json` (or `opencode.jsonc`) and remove `"oh-my-opencode"` from the `plugin` array:
+   Edit `~/.config/opencode/opencode.json` (or `opencode.jsonc`) and remove `"openagent-labforge"` from the `plugin` array:
 
    ```bash
    # Using jq
-   jq '.plugin = [.plugin[] | select(. != "oh-my-opencode")]' \
+   jq '.plugin = [.plugin[] | select(. != "openagent-labforge")]' \
        ~/.config/opencode/opencode.json > /tmp/oc.json && \
        mv /tmp/oc.json ~/.config/opencode/opencode.json
    ```
@@ -428,10 +484,10 @@ To remove oh-my-opencode:
 
    ```bash
    # Remove user config
-   rm -f ~/.config/opencode/oh-my-opencode.json ~/.config/opencode/oh-my-opencode.jsonc
+   rm -f ~/.config/opencode/openagent-labforge.json ~/.config/opencode/openagent-labforge.jsonc
 
    # Remove project config (if exists)
-   rm -f .opencode/oh-my-opencode.json .opencode/oh-my-opencode.jsonc
+   rm -f .opencode/openagent-labforge.json .opencode/openagent-labforge.jsonc
    ```
 
 3. **Verify removal**
@@ -456,7 +512,7 @@ See full [Features Documentation](docs/reference/features.md).
 - **Claude Code Compatibility**: Full hook system, commands, skills, agents, MCPs
 - **Built-in MCPs**: websearch (Exa), context7 (docs), grep_app (GitHub search)
 - **Session Tools**: List, read, search, and analyze session history
-- **Productivity Features**: Ralph Loop, Todo Enforcer, Comment Checker, Think Mode, and more
+- **Productivity Features**: Ralph Loop, Todo Enforcer, GPT permission-tail continuation, Comment Checker, Think Mode, and more
 - **Model Setup**: Agent-model matching is built into the [Installation Guide](docs/guide/installation.md#step-5-understand-your-model-setup)
 
 ## Configuration
@@ -466,14 +522,14 @@ Opinionated defaults, adjustable if you insist.
 See [Configuration Documentation](docs/reference/configuration.md).
 
 **Quick Overview:**
-- **Config Locations**: `.opencode/oh-my-opencode.jsonc` or `.opencode/oh-my-opencode.json` (project), `~/.config/opencode/oh-my-opencode.jsonc` or `~/.config/opencode/oh-my-opencode.json` (user)
+- **Config Locations**: `.opencode/openagent-labforge.jsonc` or `.opencode/openagent-labforge.json` (project), `~/.config/opencode/openagent-labforge.jsonc` or `~/.config/opencode/openagent-labforge.json` (user)
 - **JSONC Support**: Comments and trailing commas supported
 - **Agents**: Override models, temperatures, prompts, and permissions for any agent
 - **Built-in Skills**: `playwright` (browser automation), `git-master` (atomic commits)
 - **Sisyphus Agent**: Main orchestrator with Prometheus (Planner) and Metis (Plan Consultant)
 - **Background Tasks**: Configure concurrency limits per provider/model
 - **Categories**: Domain-specific task delegation (`visual`, `business-logic`, custom)
-- **Hooks**: 25+ built-in hooks, all configurable via `disabled_hooks`
+- **Hooks**: 25+ built-in hooks, including `gpt-permission-continuation`, all configurable via `disabled_hooks`
 - **MCPs**: Built-in websearch (Exa), context7 (docs), grep_app (GitHub search)
 - **LSP**: Full LSP support with refactoring tools
 - **Experimental**: Aggressive truncation, auto-resume, and more
@@ -525,3 +581,4 @@ No affiliation with any project/model mentioned. Just personal experimentation.
   - Making elepay - multi-mobile payment gateway, OneQR - mobile application SaaS for cashless solutions
 
 *Special thanks to [@junhoyeo](https://github.com/junhoyeo) for this amazing hero image.*
+