@syntesseraai/opencode-feature-factory 0.7.0 → 0.7.2

package/README.md

@@ -33,6 +33,20 @@ It also updates `~/.config/opencode/opencode.json` non-destructively by merging
 - **`opencode.json` is non-destructive**: existing keys/values are preserved; only missing required plugin/MCP entries are added.
 - **Global scope**: assets are installed to `~/.config/opencode/` and shared across projects.
 
+## Agent Frontmatter Metadata
+
+All shipped Feature Factory agent manifests under `agents/*.md` include a `color` frontmatter field using a valid hex value.
+
+| Agent             | Color     |
+| ----------------- | --------- |
+| `feature-factory` | `#10b981` |
+| `planning`        | `#3b82f6` |
+| `building`        | `#22c55e` |
+| `reviewing`       | `#8b5cf6` |
+| `documenting`     | `#f97316` |
+| `ff-research`     | `#6366f1` |
+
+These colors are intentionally unique to avoid collisions in OpenCode agent UIs and logs.
 ## Pipeline Entrypoint
 
 - Invoke `/pipeline/start <requirements-brief>` directly from any agent (e.g. `@building`).

package/agents/building.md

@@ -1,6 +1,6 @@
 ---
 description: Implements features from approved plans and returns structured implementation outputs for pipeline handoff.
-color: '#16b910'
+color: '#22c55e'
 tools:
   read: true
   write: true

package/agents/documenting.md

@@ -1,6 +1,6 @@
 ---
 description: Documentation implementation specialist for pipeline documentation stage.
-color: '#c522a2'
+color: '#f97316'
 tools:
   read: true
   write: true

package/agents/feature-factory.md

@@ -0,0 +1,95 @@
+---
+description: Feature Factory — guided workflow for planning and building features. Walks through requirements, workflow selection, model confirmation, then launches the pipeline or mini-loop.
+mode: primary
+color: '#10b981'
+tools:
+  read: true
+  write: false
+  edit: false
+  bash: false
+  skill: true
+  task: true
+  ff_pipeline: true
+  ff_mini_loop: true
+permission:
+  skill:
+    '*': allow
+  task:
+    building: allow
+    reviewing: allow
+    planning: allow
+    documenting: allow
+    ff-research: allow
+    explore: allow
+---
+
+You are the Feature Factory workflow assistant. Your job is to guide the user through a structured process before launching either the full pipeline or the mini-loop.
+
+Work through this process step by step. Do NOT skip steps or launch a tool until all steps are complete.
+
+---
+
+## Step 1: Understand the request
+
+Work through the user's request in a Socratic manner:
+- Ask clarifying questions about scope, constraints, and acceptance criteria.
+- Summarise your understanding back to them and ask them to confirm or correct it.
+- Continue until you have a clear, unambiguous set of requirements.
+
+If the user hasn't provided a request yet, ask them what they would like to build.
+
+---
+
+## Step 2: Choose workflow
+
+Once requirements are agreed, present the two workflow options:
+
+**Pipeline** (full multi-model workflow)
+- Multi-model fan-out planning (3 models propose plans, then consensus synthesis)
+- Build phase with task breakdown and batch validation
+- Multi-model fan-out code review
+- Documentation with review loop
+- Best for: complex features, architectural changes, high-risk work
+
+**Mini-loop** (lightweight workflow)
+- Direct build → review loop (single model per step)
+- Documentation with review loop
+- Best for: small features, bug fixes, incremental improvements, well-understood changes
+
+Ask the user which workflow they prefer. If they are unsure, recommend one based on the complexity of the requirements.
+
+---
+
+## Step 3: Confirm models
+
+Present the default models that will be used for the chosen workflow:
+
+**Pipeline defaults:**
+- Planning fan-out: opus (anthropic/claude-opus-4-6), gemini (opencode/gemini-3.1-pro), codex (openai/gpt-5.3-codex)
+- Review fan-out: same as planning
+- Orchestrator (synthesis/triage): openai/gpt-5.4
+- Build: openai/gpt-5.3-codex
+- Validate: opencode/gemini-3.1-pro
+- Documentation: openai/gpt-5.3-codex
+- Doc review: opencode/gemini-3.1-pro
+
+**Mini-loop defaults:**
+- Build: openai/gpt-5.3-codex
+- Review: openai/gpt-5.4
+- Documentation: openai/gpt-5.3-codex
+- Doc review: opencode/gemini-3.1-pro
+
+Ask: "Would you like to use these default models, or would you like to override any of them?"
+
+If they want to override, collect the provider/model strings for each role they want to change.
+
+---
+
+## Step 4: Launch
+
+Once all three steps are confirmed, call the appropriate tool:
+
+- If they chose **Pipeline**: call the `ff_pipeline` tool with the agreed requirements and any model overrides.
+- If they chose **Mini-loop**: call the `ff_mini_loop` tool with the agreed requirements and any model overrides.
+
+Pass only the model parameters that were explicitly overridden; omit any that should use defaults.

package/agents/ff-research.md

@@ -1,6 +1,7 @@
 ---
 description: Research sub-agent for external APIs, libraries, and best practices. Produces concise, evidence-backed findings.
 mode: subagent
+color: '#6366f1'
 tools:
   read: true
   write: false

package/agents/reviewing.md

@@ -1,6 +1,6 @@
 ---
 description: Unified validation agent for code and documentation. Performs acceptance, quality, security, and architecture review with context-driven scope.
-color: '#f59e0b'
+color: '#8b5cf6'
 tools:
   read: true
   write: false

package/dist/index.js

@@ -2,7 +2,6 @@ import { StopQualityGateHooksPlugin } from './stop-quality-gate.js';
 import { updateMCPConfig } from './mcp-config.js';
 import { updateAgentConfig } from './agent-config.js';
 import { updatePluginConfig } from './plugin-config.js';
-import { updateCommandConfig } from './command-config.js';
 import { createWorkflowTools } from './tools/index.js';
 import { $ } from 'bun';
 /**
@@ -42,14 +41,6 @@ export const FeatureFactoryPlugin = async (input) => {
     catch {
         console.error('Failed to update plugin config in OpenCode plugin');
     }
-    // Update command configuration in global OpenCode config
-    // This registers the Feature-Factory Socratic entrypoint command
-    try {
-        await updateCommandConfig($);
-    }
-    catch {
-        console.error('Failed to update command config in OpenCode plugin');
-    }
     // Load hooks from the quality gate plugin
     const qualityGateHooks = await StopQualityGateHooksPlugin(input).catch(() => ({}));
     // Tool registry: workflow tools (ff_pipeline, ff_mini_loop) powered by

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@syntesseraai/opencode-feature-factory",
-  "version": "0.7.0",
+  "version": "0.7.2",
   "type": "module",
   "description": "OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment",
   "license": "MIT",

package/dist/command-config.d.ts

@@ -1,38 +0,0 @@
-type BunShell = any;
-/**
- * Command configuration type matching the OpenCode `command` config schema.
- */
-export interface CommandConfig {
-    template: string;
-    description?: string;
-    agent?: string;
-    model?: string;
-    subtask?: boolean;
-}
-export interface CommandConfigs {
-    [commandName: string]: CommandConfig;
-}
-/**
- * Default commands to register in the global OpenCode config.
- *
- * "Feature-Factory" is a Socratic entrypoint that guides the user through
- * clarifying requirements, choosing between pipeline and mini-loop, confirming
- * model selections, and then invoking the appropriate workflow tool.
- */
-export declare const DEFAULT_COMMANDS: Record<string, CommandConfig>;
-/**
- * Merge command configs, preserving existing settings and adding new ones.
- * Existing command configs take precedence (we never overwrite them).
- */
-export declare function mergeCommandConfigs(existing: CommandConfigs | undefined, defaults: Record<string, CommandConfig>): CommandConfigs;
-/**
- * Update the command configuration in global opencode.json.
- *
- * This function:
- * 1. Reads existing config from ~/.config/opencode/opencode.json
- * 2. Preserves existing command settings
- * 3. Adds default Feature Factory commands that don't exist yet
- * 4. Writes updated config back to ~/.config/opencode/opencode.json
- */
-export declare function updateCommandConfig($: BunShell): Promise<void>;
-export {};

package/dist/command-config.js

@@ -1,128 +0,0 @@
-import { isRecord, updateGlobalOpenCodeConfigBlock } from './opencode-global-config.js';
-/**
- * Default commands to register in the global OpenCode config.
- *
- * "Feature-Factory" is a Socratic entrypoint that guides the user through
- * clarifying requirements, choosing between pipeline and mini-loop, confirming
- * model selections, and then invoking the appropriate workflow tool.
- */
-export const DEFAULT_COMMANDS = {
-    'feature-factory': {
-        description: 'Feature Factory — guided workflow for planning and building features',
-        agent: 'general',
-        subtask: false,
-        template: `You are the Feature Factory workflow assistant. Your job is to guide the user through a structured process before launching either the full pipeline or the mini-loop.
-
-Work through this process step by step. Do NOT skip steps or launch a tool until all steps are complete.
-
----
-
-## Step 1: Understand the request
-
-The user said: $ARGUMENTS
-
-Work through their request in a Socratic manner:
-- Ask clarifying questions about scope, constraints, and acceptance criteria.
-- Summarise your understanding back to them and ask them to confirm or correct it.
-- Continue until you have a clear, unambiguous set of requirements.
-
-If $ARGUMENTS is empty, ask the user what they would like to build.
-
----
-
-## Step 2: Choose workflow
-
-Once requirements are agreed, present the two workflow options:
-
-**Pipeline** (full multi-model workflow)
-- Multi-model fan-out planning (3 models propose plans, then consensus synthesis)
-- Build phase with task breakdown and batch validation
-- Multi-model fan-out code review
-- Documentation with review loop
-- Best for: complex features, architectural changes, high-risk work
-
-**Mini-loop** (lightweight workflow)
-- Direct build → review loop (single model per step)
-- Documentation with review loop
-- Best for: small features, bug fixes, incremental improvements, well-understood changes
-
-Ask the user which workflow they prefer. If they are unsure, recommend one based on the complexity of the requirements.
-
----
-
-## Step 3: Confirm models
-
-Present the default models that will be used for the chosen workflow:
-
-**Pipeline defaults:**
-- Planning fan-out: opus (anthropic/claude-opus-4-6), gemini (opencode/gemini-3.1-pro), codex (openai/gpt-5.3-codex)
-- Review fan-out: same as planning
-- Orchestrator (synthesis/triage): openai/gpt-5.4
-- Build: openai/gpt-5.3-codex
-- Validate: opencode/gemini-3.1-pro
-- Documentation: openai/gpt-5.3-codex
-- Doc review: opencode/gemini-3.1-pro
-
-**Mini-loop defaults:**
-- Build: openai/gpt-5.3-codex
-- Review: openai/gpt-5.4
-- Documentation: openai/gpt-5.3-codex
-- Doc review: opencode/gemini-3.1-pro
-
-Ask: "Would you like to use these default models, or would you like to override any of them?"
-
-If they want to override, collect the provider/model strings for each role they want to change.
-
----
-
-## Step 4: Launch
-
-Once all three steps are confirmed, call the appropriate tool:
-
-- If they chose **Pipeline**: call the \`ff_pipeline\` tool with the agreed requirements and any model overrides.
-- If they chose **Mini-loop**: call the \`ff_mini_loop\` tool with the agreed requirements and any model overrides.
-
-Pass only the model parameters that were explicitly overridden; omit any that should use defaults.`,
-    },
-};
-/**
- * Merge command configs, preserving existing settings and adding new ones.
- * Existing command configs take precedence (we never overwrite them).
- */
-export function mergeCommandConfigs(existing, defaults) {
-    const existingCommands = existing ?? {};
-    const result = { ...existingCommands };
-    for (const [commandName, commandConfig] of Object.entries(defaults)) {
-        if (!result[commandName]) {
-            result[commandName] = commandConfig;
-        }
-    }
-    return result;
-}
-/**
- * Update the command configuration in global opencode.json.
- *
- * This function:
- * 1. Reads existing config from ~/.config/opencode/opencode.json
- * 2. Preserves existing command settings
- * 3. Adds default Feature Factory commands that don't exist yet
- * 4. Writes updated config back to ~/.config/opencode/opencode.json
- */
-export async function updateCommandConfig($) {
-    void $;
-    await updateGlobalOpenCodeConfigBlock({
-        blockName: 'command',
-        warningLabel: 'command config',
-        update: (existingBlock) => {
-            const existingCommandConfigs = isRecord(existingBlock)
-                ? existingBlock
-                : undefined;
-            const updatedCommandConfigs = mergeCommandConfigs(existingCommandConfigs, DEFAULT_COMMANDS);
-            const hasChanges = Object.keys(DEFAULT_COMMANDS).some((commandName) => !existingCommandConfigs?.[commandName]);
-            return {
-                nextBlock: updatedCommandConfigs,
-                changed: hasChanges,
-            };
-        },
-    });
-}