aidevops 3.32.316 → 3.32.318

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -1,7 +1,7 @@
1
1
  <!-- SPDX-License-Identifier: MIT -->
2
2
  <!-- SPDX-FileCopyrightText: 2025-2026 Marcus Quinn -->
3
3
 
4
- ![AI DevOps — 15 main agents, 2,250+ sub agents, 2,140+ helper scripts, and 100+ slash commands](docs/assets/og-image.png)
4
+ ![AI DevOps — 14 main agents, 2,200+ sub agents, 2,010+ helper scripts, and 100+ slash commands](docs/assets/og-image.png)
5
5
 
6
6
  # AI DevOps Framework
7
7
 
@@ -60,7 +60,7 @@ The result: an AI operations platform that manages projects across every busines
60
60
  [![Copyright](https://img.shields.io/badge/Copyright-Marcus%20Quinn%202025--2026-blue.svg)](https://github.com/marcusquinn)
61
61
 
62
62
  <!-- Release & Version Info -->
63
- [![Version](https://img.shields.io/badge/Version-3.32.316-blue.svg)](https://github.com/marcusquinn/aidevops/releases)
63
+ [![Version](https://img.shields.io/badge/Version-3.32.318-blue.svg)](https://github.com/marcusquinn/aidevops/releases)
64
64
  [![npm version](https://img.shields.io/npm/v/aidevops)](https://www.npmjs.com/package/aidevops)
65
65
  [![Homebrew](https://img.shields.io/badge/homebrew-marcusquinn%2Ftap-orange)](https://github.com/marcusquinn/homebrew-tap)
66
66
  [![GitHub repository](https://img.shields.io/badge/github-repository-181717.svg?logo=github)](https://github.com/marcusquinn/aidevops)
@@ -126,12 +126,16 @@ the required notices and preferred credit text.
126
126
 
127
127
  ### Agent Structure
128
128
 
129
- - 15 primary agents (Build+, Automate, Product, SEO, Marketing-Sales, etc.) with specialist @subagents on demand
130
- - 2,250+ supporting Markdown guides: subagents, skills, references, templates, commands, and workflows organized by domain
131
- - 2,140+ scripts in `.agents/scripts/` (shell helpers and tests)
132
- - 100+ slash commands and 100+ workflow guides for common operations
129
+ - 14 main agents (Build+, Automate, Product, SEO, Marketing-Sales, etc.) with specialist @subagents on demand
130
+ - 2,200+ sub agents: individually callable Markdown modules, including skills, workflows and specialist references
131
+ - 2,010+ helper scripts across scripting languages, including supporting production modules but excluding tests
132
+ - 100+ slash commands for common operations
133
133
 
134
- Counts checked on 5 September 2026: 15 root agent files (excluding `AGENTS.md`), 2,268 regular Markdown files in `.agents/` subdirectories (excluding symlink aliases), 2,146 shell scripts, 106 slash-command entry points, and 104 workflow guides. Command and workflow source guides are included in the supporting-guide total, not additional agents. See [hero count maintenance](DESIGN.md#readme-hero-counts) for sources and refresh instructions.
134
+ <!-- aidevops:inventory:start -->
135
+ Exact source inventory: **14 main agents**, **2,236 sub agents**, **2,017 helper scripts**, **106 slash commands**.
136
+ <!-- aidevops:inventory:end -->
137
+
138
+ These are tracked source modules and entry points, not counts of running agents. Main agents follow the runtime's discovery exclusions. Sub agents are individually addressable Markdown instruction modules selected by the generator's filename rules, regardless of `mode` metadata; callable skills, workflows and references count too. This measures distinct source paths, not unique flattened runtime names. Helper scripts include production script files and supporting modules across scripting languages, not just `*-helper` filenames. Tests, fixtures, generated/vendor files and duplicate aliases are excluded. Slash commands include valid shipped aliases; their regular source modules also belong to the sub-agent library, so the categories must not be added together. Audit every included path with `bash .agents/scripts/readme-helper.sh counts --inventory`; see [counting rules and hero maintenance](DESIGN.md#readme-hero-counts).
135
139
 
136
140
  ### What You Can Ask aidevops To Do
137
141
 
@@ -315,6 +319,10 @@ aidevops update-tools # Check and update installed tools
315
319
  aidevops uninstall # Remove aidevops
316
320
  ```
317
321
 
322
+ ### Optional Blender Lab MCP
323
+
324
+ [Blender MCP guidance](.agents/tools/design/blender.md) covers source-specific setup, scene analysis, Python API lookup, and the distinction between Blender's Lab project and the independent community `blender-mcp` package. Includes opt-in [OpenCode](configs/blender-lab-opencode-config.json.txt) and [MCP client](configs/blender-lab-mcp-config.json.txt) templates. Nothing is installed or activated automatically: Blender executes generated Python without protective guards, so use an isolated system and disposable scene copies.
325
+
318
326
  ### Optional Design Artifact Studio
319
327
 
320
328
  aidevops now treats design as a self-contained stack with optional peripherals:
@@ -842,9 +850,9 @@ aidevops implements proven agent design patterns identified by [Lance Martin (La
842
850
 
843
851
  | Pattern | Description | aidevops Implementation |
844
852
  |---------|-------------|------------------------|
845
- | **Give Agents a Computer** | Filesystem + shell for persistent context | `~/.aidevops/.agent-workspace/`, 2,140+ scripts (shell helpers and tests) |
853
+ | **Give Agents a Computer** | Filesystem + shell for persistent context | `~/.aidevops/.agent-workspace/`, 2,010+ helper scripts |
846
854
  | **Multi-Layer Action Space** | Few tools, push actions to computer | Per-agent MCP filtering (~12-20 tools each) |
847
- | **Knowledge Graph Routing** | Indexed, cross-referenced agents instead of isolated skills | `subagent-index.toon` routes agent context within a library of 2,250+ supporting guides — agents discover related context through the graph, not just their own file |
855
+ | **Knowledge Graph Routing** | Indexed, cross-referenced agents instead of isolated skills | `subagent-index.toon` routes context across subagent profiles and the wider skills/documentation library — agents discover related context through the graph, not just their own file |
848
856
  | **Progressive Disclosure** | Load context on-demand | Subagent routing with content summaries, YAML frontmatter, read-on-demand |
849
857
  | **Offload Context** | Write results to filesystem | `.agent-workspace/work/[project]/` for persistence |
850
858
  | **Cache Context** | Prompt caching for cost | Stable instruction prefixes |
@@ -1334,6 +1342,7 @@ The setup script offers to install these tools automatically.
1334
1342
 
1335
1343
  ### **Video Creation**
1336
1344
 
1345
+ - **[Video-use](https://github.com/browser-use/video-use)**: Conversational footage editing through the [video-editor runtime adapter](.agents/tools/video/video-use-runtime.md), with a reviewed executable pin, explicit installation, whole-repository update checks and a no-upload synthetic render smoke test. Run `python3 ~/.aidevops/agents/scripts/video-use-helper.py status` to check readiness.
1337
1346
  - **[Remotion](https://remotion.dev/)**: Programmatic video creation with React - animations, compositions, media handling, captions
1338
1347
  - **[Video Prompt Design](https://github.com/snubroot/Veo-3-Meta-Framework)**: AI video prompt engineering using the 7-component meta prompt framework for Veo 3 and similar models
1339
1348
  - **[Kie.ai](https://kie.ai/)**: Unified asynchronous Market API and `kie-helper.sh` workflow for image, video, audio, uploads, callbacks, and credit checks with model-specific JSON pass-through
@@ -1904,7 +1913,7 @@ aidevops is registered as a **Claude Code plugin marketplace**. Install with two
1904
1913
  /plugin install aidevops@aidevops
1905
1914
  ```
1906
1915
 
1907
- This installs the complete framework: 15 primary agents, 2,250+ supporting guides, and 2,140+ scripts (shell helpers and tests).
1916
+ This installs the complete framework: 14 main agents, 2,200+ sub agents, and 2,010+ helper scripts, including callable skill/reference modules and supporting production script code.
1908
1917
 
1909
1918
  ### Importing External Skills
1910
1919
 
@@ -2057,7 +2066,7 @@ The long-term direction is to make slash commands and `@mentions` unnecessary al
2057
2066
 
2058
2067
  ### **Example Subagents with MCP Integration**
2059
2068
 
2060
- These are examples of subagents that have supporting MCPs enabled. See `.agents/` for the library of 2,250+ supporting guides organized by domain.
2069
+ These are examples of subagents that have supporting MCPs enabled. See `.agents/` for 2,200+ sub agents, including callable skill, workflow and reference modules organized by domain.
2061
2070
 
2062
2071
  | Agent | Purpose | MCPs Enabled |
2063
2072
  |-------|---------|--------------|
@@ -2764,8 +2773,8 @@ aidevops/
2764
2773
  ├── AGENTS.md # AI agent guidance (dev)
2765
2774
  ├── .agents/ # Agents and documentation
2766
2775
  │ ├── AGENTS.md # User guide (deployed to ~/.aidevops/agents/)
2767
- │ ├── *.md # 15 primary agents
2768
- │ ├── scripts/ # 2,140+ shell scripts (helpers and tests)
2776
+ │ ├── *.md # 14 main agents, plus excluded root guides
2777
+ │ ├── scripts/ # 2,010+ helper scripts (including modules; tests excluded)
2769
2778
  │ ├── tools/ # Cross-domain utilities (video, browser, git, etc.)
2770
2779
  │ ├── services/ # External service integrations
2771
2780
  │ └── workflows/ # Development process guides
@@ -2889,7 +2898,7 @@ See `.agents/tools/credentials/multi-tenant.md` for complete documentation.
2889
2898
  - Autonomous supervisor — pulse runs every 2 minutes, merging PRs, dispatching workers, killing stuck processes, advancing missions
2890
2899
  - Operational intelligence — struggle-ratio detection, orphaned PR recovery, circuit breaker, dynamic concurrency
2891
2900
  - Cost-aware routing — provider-aware model selection across OpenAI, Anthropic, Gemini, Cursor, Grok, and local models with budget tracking
2892
- - Progressive context — 2,250+ supporting guides available on demand, project bundles auto-configuring quality gates and model tiers
2901
+ - Progressive context — 2,200+ sub agents available on demand, project bundles auto-configuring quality gates and model tiers
2893
2902
  - Self-improving — session mining extracts learnings, quality findings auto-create tasks, patterns feed back into agent prompts
2894
2903
 
2895
2904
  **Get Started:**
package/VERSION CHANGED
@@ -1 +1 @@
1
- 3.32.316
1
+ 3.32.318
package/aidevops.sh CHANGED
@@ -5,7 +5,7 @@
5
5
  # AI DevOps Framework CLI
6
6
  # Usage: aidevops <command> [options]
7
7
  #
8
- # Version: 3.32.316
8
+ # Version: 3.32.318
9
9
 
10
10
  set -euo pipefail
11
11
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "aidevops",
3
- "version": "3.32.316",
3
+ "version": "3.32.318",
4
4
  "description": "AI DevOps Framework - AI-assisted development workflows, code quality, and deployment automation",
5
5
  "type": "module",
6
6
  "packageManager": "bun@1.3.11",
package/setup.sh CHANGED
@@ -17,7 +17,7 @@ fi
17
17
  # AI Assistant Server Access Framework Setup Script
18
18
  # Helps developers set up the framework for their infrastructure
19
19
  #
20
- # Version: 3.32.316
20
+ # Version: 3.32.318
21
21
  #
22
22
  # Quick Install:
23
23
  # npm install -g aidevops && aidevops update (recommended)