opencode-athena 0.2.0 → 0.4.0

package/README.md

@@ -43,6 +43,7 @@ The interactive installer will:
   - Claude Pro/Max (recommended)
   - ChatGPT Plus/Pro
   - Google/Gemini
+  - GitHub Copilot (Free/Pro/Pro+/Business/Enterprise)
 
 ## Commands
 
@@ -192,16 +193,196 @@ Configuration files are stored in `~/.config/opencode/`:
 Use `--preset` during installation:
 
 ```bash
-npx opencode-athena install --preset minimal    # Bare essentials
-npx opencode-athena install --preset standard   # Recommended (default)
-npx opencode-athena install --preset enterprise # Full features
-npx opencode-athena install --preset solo-quick # Solo dev quick flow
+npx opencode-athena install --preset minimal     # Bare essentials
+npx opencode-athena install --preset standard    # Recommended (default)
+npx opencode-athena install --preset enterprise  # Full features
+npx opencode-athena install --preset solo-quick  # Solo dev quick flow
+npx opencode-athena install --preset copilot-only # GitHub Copilot users
 ```
 
 ### Project Overrides
 
 Create `.opencode/athena.json` in your project root to override global settings.
 
+### Model Settings
+
+Athena provides fine-grained control over model behavior through `temperature` and `thinkingLevel` settings. These can be configured per agent role in `athena.json`:
+
+```json
+{
+  "models": {
+    "settings": {
+      "sisyphus": {
+        "temperature": 0.3,
+        "thinkingLevel": "medium"
+      },
+      "oracle": {
+        "thinkingLevel": "high"
+      },
+      "librarian": {
+        "temperature": 0.2
+      }
+    }
+  }
+}
+```
+
+**Temperature** controls response randomness. Valid range is provider-specific:
+- Anthropic: 0.0-1.0
+- OpenAI: 0.0-2.0
+- Google: 0.0-2.0
+- GitHub Copilot: Not supported
+
+Lower values = more focused, higher = more creative. Defaults are model-family-aware and clamped to valid ranges.
+
+**ThinkingLevel** controls reasoning depth for supported models:
+- `"low"` - Quick responses, minimal reasoning
+- `"medium"` - Balanced (default)
+- `"high"` - Deep reasoning, slower
+
+ThinkingLevel maps to provider-specific parameters:
+| Provider | Parameter | Values |
+|----------|-----------|--------|
+| Anthropic | `thinking.budget_tokens` | 4096 / 16384 / 32768 |
+| OpenAI | `reasoning_effort` | `"low"` / `"medium"` / `"high"` |
+| Google | `thinking_level` | `"low"` / `"medium"` / `"high"` |
+
+Note: Temperature and thinkingLevel are not supported for GitHub Copilot-routed models.
+
+### Custom Models
+
+Add custom models to use models not in the built-in list. Custom models can override built-in models or add entirely new ones:
+
+```json
+{
+  "models": {
+    "sisyphus": "custom/my-finetuned-model",
+    "custom": [
+      {
+        "id": "custom/my-finetuned-model",
+        "name": "My Fine-tuned Model",
+        "provider": "openai",
+        "description": "Custom fine-tuned GPT for our codebase",
+        "capabilities": {
+          "thinking": false,
+          "contextWindow": 128000,
+          "supportsTemperature": true
+        }
+      },
+      {
+        "id": "anthropic/claude-4-opus",
+        "name": "Claude 4 Opus (Override)",
+        "provider": "anthropic",
+        "description": "Override built-in model with custom settings"
+      }
+    ]
+  }
+}
+```
+
+Custom model fields:
+- `id` (required): Unique identifier, format: `provider/model-name`
+- `name` (required): Display name
+- `provider` (required): `"anthropic"`, `"openai"`, `"google"`, or `"github-copilot"`
+- `description`: Optional description
+- `capabilities`: Optional capability hints
+  - `thinking`: Whether the model supports extended thinking
+  - `contextWindow`: Context window size in tokens
+  - `supportsTemperature`: Whether temperature can be adjusted
+
+### Git Operations Policy
+
+By default, Athena prevents agents from automatically performing git operations (commits, pushes, branch creation). This ensures developers maintain full control over version control.
+
+**Default behavior** (`autoGitOperations: false`):
+- ✅ Agents can read git state (`git status`, `git diff`, `git log`)
+- ❌ Agents cannot automatically commit, push, or create branches
+- ⚠️ If an agent attempts a git write operation, a warning is injected
+- 📝 Agents must ask for explicit user permission before git operations
+
+**Enable automatic git operations:**
+
+Set `features.autoGitOperations: true` in `athena.json`:
+
+```json
+{
+  "features": {
+    "autoGitOperations": true
+  }
+}
+```
+
+Or during installation, check the "Auto Git Operations" feature.
+
+**Covered operations:**
+- **Git commits & pushes:** `git commit`, `git push`
+- **Branch operations:** `git checkout -b`, `git branch`, `git switch -c`, `git switch --create`
+- **Merging & rebasing:** `git merge`, `git rebase`, `git cherry-pick`
+- **Stashing & tags:** `git stash`, `git tag`
+- **Reset operations:** `git reset` (all variants: --soft, --mixed, --hard)
+- **GitHub PR operations:** `gh pr create`, `gh pr edit`, `gh pr merge`, `gh pr close`, `gh pr review`
+- **GitHub issue operations:** `gh issue create`, `gh issue edit`, `gh issue close`
+- **GitHub release operations:** `gh release create`, `gh release edit`, `gh release delete`
+
+**Why this is the default:**
+
+Version control is critical. Automatic commits can:
+- Create unclear commit messages
+- Commit unintended changes
+- Disrupt branch strategies
+- Bypass code review processes
+
+With `autoGitOperations: false`, agents track progress via `athena_update_status()` instead, which updates `sprint-status.yaml` without git operations.
+
+## GitHub Copilot Support
+
+Athena supports GitHub Copilot as a model provider, allowing you to use Claude, GPT, and Gemini models through your Copilot subscription. This is especially useful for enterprise users who only have access to LLMs through Copilot.
+
+### Setup
+
+1. Run the installer and select "GitHub Copilot" when asked about subscriptions
+2. Select your Copilot plan level (determines available models)
+3. After installation, authenticate:
+   ```bash
+   opencode auth login github-copilot
+   ```
+
+Or use the `copilot-only` preset:
+```bash
+npx opencode-athena install --preset copilot-only
+```
+
+### Plan Levels and Models
+
+Model availability depends on your GitHub Copilot plan:
+
+| Plan | Claude Models | GPT Models | Gemini Models |
+|------|---------------|------------|---------------|
+| **Free** | Haiku 4.5 | GPT-4.1, GPT-5-mini | - |
+| **Pro** | Haiku 4.5, Sonnet 4, Sonnet 4.5 | GPT-4.1, GPT-5, GPT-5-mini, GPT-5.1, GPT-5.1-codex, GPT-5.2 | Gemini 2.5 Pro, Gemini 3 Flash, Gemini 3 Pro |
+| **Pro+** | All Pro models + Opus 4.1, Opus 4.5 | All Pro models | All Pro models |
+| **Business** | Haiku 4.5, Sonnet 4, Sonnet 4.5 | GPT-4.1, GPT-5, GPT-5-mini, GPT-5.1, GPT-5.1-codex, GPT-5.2 | Gemini 2.5 Pro, Gemini 3 Flash, Gemini 3 Pro |
+| **Enterprise** | All Pro models + Opus 4.1, Opus 4.5 | All Pro models | All Pro models |
+
+### How It Works
+
+GitHub Copilot acts as a proxy to multiple LLM providers. When you configure a Copilot-routed model (e.g., `github-copilot/claude-sonnet-4`), requests are sent through GitHub's API.
+
+**Naming convention:** Copilot-routed models use the format `github-copilot/{model}` (e.g., `github-copilot/gpt-4o`).
+
+**Priority behavior:** If you have both direct provider access and Copilot access (e.g., Claude Pro + Copilot), Athena prefers direct provider models for better feature support.
+
+### Limitations
+
+Models accessed through GitHub Copilot have some limitations compared to direct provider access:
+
+- **No temperature control**: Copilot strips temperature parameters
+- **No thinking/reasoning modes**: Extended thinking (Claude), reasoning effort (OpenAI), and thinking level (Google) are not supported
+- **Rate limits**: Subject to Copilot's rate limits rather than provider limits
+- **Feature lag**: New model features may not be immediately available
+
+For full model capabilities, use direct provider subscriptions when possible.
+
 ## Architecture
 
 ```

package/commands/athena-debug.md

@@ -4,6 +4,44 @@ description: Debug an issue using Oracle's deep reasoning capabilities
 
 # Athena Debug - Oracle-Powered Debugging
 
+## Git Operations Policy
+
+**⚠️ AUTOMATIC GIT OPERATIONS ARE PROHIBITED**
+
+You must NOT perform any git operations automatically:
+- ❌ Do NOT run `git commit` to save changes
+- ❌ Do NOT run `git push` to push to remote
+- ❌ Do NOT run `git checkout -b` or `git branch` to create branches
+- ❌ Do NOT run `git merge`, `git rebase`, or `git cherry-pick`
+- ❌ Do NOT run `gh pr create` or other GitHub CLI operations
+
+**Git operations are ONLY permitted if the user explicitly requests them.**
+
+Examples of explicit permission:
+- User says: "Please commit these fixes"
+- User says: "Create a branch for this bugfix"
+- User says: "Push to origin" or "Create a PR"
+
+**If you believe git operations would be helpful, ASK the user first:**
+```
+I've fixed the issue. Would you like me to:
+1. Commit the fix to git, or
+2. Leave git operations for you to handle manually?
+```
+
+**To track story progress without git, use:**
+```
+athena_update_status({
+  storyId: "X.Y",
+  status: "in_progress",
+  notes: "Fixed issue: [description]"
+})
+```
+
+This updates sprint-status.yaml without requiring git commits.
+
+---
+
 Use Oracle, the debugging specialist, to analyze and fix complex issues with systematic hypothesis-driven debugging.
 
 **You are Sisyphus, the orchestrator.** You will coordinate Oracle's deep reasoning with automated tools to efficiently diagnose and fix issues.

package/commands/athena-dev.md

@@ -4,6 +4,44 @@ description: Implement the current BMAD story using Sisyphus and specialized sub
 
 # Athena Dev - Story Implementation
 
+## Git Operations Policy
+
+**⚠️ AUTOMATIC GIT OPERATIONS ARE PROHIBITED**
+
+You must NOT perform any git operations automatically:
+- ❌ Do NOT run `git commit` to save changes
+- ❌ Do NOT run `git push` to push to remote
+- ❌ Do NOT run `git checkout -b` or `git branch` to create branches
+- ❌ Do NOT run `git merge`, `git rebase`, or `git cherry-pick`
+- ❌ Do NOT run `gh pr create` or other GitHub CLI operations
+
+**Git operations are ONLY permitted if the user explicitly requests them.**
+
+Examples of explicit permission:
+- User says: "Please commit these changes"
+- User says: "Create a branch called feature-x"
+- User says: "Push to origin" or "Create a PR"
+
+**If you believe git operations would be helpful, ASK the user first:**
+```
+I've completed the implementation. Would you like me to:
+1. Commit these changes to git, or
+2. Leave git operations for you to handle manually?
+```
+
+**To track story progress without git, use:**
+```
+athena_update_status({
+  storyId: "X.Y",
+  status: "completed",
+  completionSummary: "What was implemented..."
+})
+```
+
+This updates sprint-status.yaml without requiring git commits.
+
+---
+
 You are implementing a BMAD story using OpenCode Athena's full capabilities.
 
 **You are Sisyphus, the orchestrator.** You will coordinate subagents and tools to implement this story efficiently and correctly.

package/commands/athena-parallel.md

@@ -8,6 +8,23 @@ description: Work on multiple stories in parallel using background agents
 > 
 > This command describes **planned functionality** that is not yet available. The `athena_parallel` tool is a placeholder. This document describes the intended behavior for future implementation.
 
+## Git Operations Policy
+
+**⚠️ AUTOMATIC GIT OPERATIONS ARE PROHIBITED**
+
+You must NOT perform any git operations automatically:
+- ❌ Do NOT run `git commit` to save changes
+- ❌ Do NOT run `git push` to push to remote
+- ❌ Do NOT run `git checkout -b` or `git branch` to create branches
+- ❌ Do NOT run `git merge`, `git rebase`, or `git cherry-pick`
+- ❌ Do NOT run `gh pr create` or other GitHub CLI operations
+
+**Git operations are ONLY permitted if the user explicitly requests them.**
+
+When working on multiple stories in parallel, git operations become especially important to coordinate manually. Always ask the user before performing any git operations.
+
+---
+
 Execute multiple BMAD stories simultaneously using background agents for maximum throughput.
 
 ## Planned Behavior

package/commands/athena-research.md

@@ -4,6 +4,23 @@ description: Research patterns, implementations, or documentation using Libraria
 
 # Athena Research - Librarian-Powered Research
 
+## Git Operations Policy
+
+**⚠️ AUTOMATIC GIT OPERATIONS ARE PROHIBITED**
+
+You must NOT perform any git operations automatically:
+- ❌ Do NOT run `git commit` to save changes
+- ❌ Do NOT run `git push` to push to remote
+- ❌ Do NOT run `git checkout -b` or `git branch` to create branches
+- ❌ Do NOT run `git merge`, `git rebase`, or `git cherry-pick`
+- ❌ Do NOT run `gh pr create` or other GitHub CLI operations
+
+**Git operations are ONLY permitted if the user explicitly requests them.**
+
+This command focuses on research and should rarely involve git operations. If you believe git operations are needed, ASK the user first.
+
+---
+
 Use Librarian, the research specialist, to find patterns, examples, and documentation from multiple sources.
 
 **You are Sisyphus, the orchestrator.** You will coordinate Librarian's research capabilities with Explore for comprehensive information gathering.

package/commands/athena-review.md

@@ -4,6 +4,44 @@ description: Run a combined quality gate on the current story implementation
 
 # Athena Review - Automated Quality Gate
 
+## Git Operations Policy
+
+**⚠️ AUTOMATIC GIT OPERATIONS ARE PROHIBITED**
+
+You must NOT perform any git operations automatically:
+- ❌ Do NOT run `git commit` to save changes
+- ❌ Do NOT run `git push` to push to remote
+- ❌ Do NOT run `git checkout -b` or `git branch` to create branches
+- ❌ Do NOT run `git merge`, `git rebase`, or `git cherry-pick`
+- ❌ Do NOT run `gh pr create` or other GitHub CLI operations
+
+**Git operations are ONLY permitted if the user explicitly requests them.**
+
+Examples of explicit permission:
+- User says: "Please commit these changes"
+- User says: "Create a branch called feature-x"
+- User says: "Push to origin" or "Create a PR"
+
+**If you believe git operations would be helpful, ASK the user first:**
+```
+The quality gate passed! Would you like me to:
+1. Commit these changes to git, or
+2. Leave git operations for you to handle manually?
+```
+
+**To track story progress without git, use:**
+```
+athena_update_status({
+  storyId: "X.Y",
+  status: "completed",
+  completionSummary: "What was implemented..."
+})
+```
+
+This updates sprint-status.yaml without requiring git commits.
+
+---
+
 Perform a comprehensive quality review by orchestrating **oh-my-opencode Oracle code review** and **BMAD adversarial review**, both powered by Oracle's deep reasoning capabilities.
 
 **You are Sisyphus, the orchestrator.** You will coordinate multiple review perspectives and synthesize the findings.

package/commands/athena-status.md

@@ -4,6 +4,23 @@ description: View and manage BMAD sprint status
 
 # Athena Status - Sprint Status Management
 
+## Git Operations Policy
+
+**⚠️ AUTOMATIC GIT OPERATIONS ARE PROHIBITED**
+
+You must NOT perform any git operations automatically:
+- ❌ Do NOT run `git commit` to save changes
+- ❌ Do NOT run `git push` to push to remote
+- ❌ Do NOT run `git checkout -b` or `git branch` to create branches
+- ❌ Do NOT run `git merge`, `git rebase`, or `git cherry-pick`
+- ❌ Do NOT run `gh pr create` or other GitHub CLI operations
+
+**Git operations are ONLY permitted if the user explicitly requests them.**
+
+This command focuses on status management and should not involve git operations.
+
+---
+
 View current sprint progress and manage story statuses. This command helps you track where you are in the sprint and what to work on next.
 
 ## Quick Status Check

package/config/presets/copilot-only.json

@@ -0,0 +1,38 @@
+{
+  "$schema": "../schemas/athena.schema.json",
+  "version": "0.0.1",
+  "description": "Configuration for users with only GitHub Copilot access (Business/Enterprise)",
+  "subscriptions": {
+    "claude": { "enabled": false, "tier": "none" },
+    "openai": { "enabled": false },
+    "google": { "enabled": false, "authMethod": "none" },
+    "githubCopilot": { "enabled": true, "plan": "business" }
+  },
+  "models": {
+    "sisyphus": "github-copilot/claude-sonnet-4.5",
+    "oracle": "github-copilot/gpt-5.1",
+    "librarian": "github-copilot/claude-haiku-4.5",
+    "frontend": "github-copilot/claude-sonnet-4.5",
+    "documentWriter": "github-copilot/gemini-2.5-pro",
+    "multimodalLooker": "github-copilot/gemini-2.5-pro"
+  },
+  "bmad": {
+    "defaultTrack": "bmad-method",
+    "autoStatusUpdate": true,
+    "parallelStoryLimit": 3
+  },
+  "features": {
+    "bmadBridge": true,
+    "autoStatus": true,
+    "parallelExecution": true,
+    "notifications": true,
+    "contextMonitor": true,
+    "commentChecker": true,
+    "lspTools": true
+  },
+  "mcps": {
+    "context7": true,
+    "exa": true,
+    "grepApp": true
+  }
+}

package/config/presets/enterprise.json

@@ -5,7 +5,8 @@
   "subscriptions": {
     "claude": { "enabled": true, "tier": "max20x" },
     "openai": { "enabled": true },
-    "google": { "enabled": true, "authMethod": "antigravity" }
+    "google": { "enabled": true, "authMethod": "antigravity" },
+    "githubCopilot": { "enabled": false, "plan": "none" }
   },
   "models": {
     "sisyphus": "anthropic/claude-opus-4-5-thinking",
@@ -13,7 +14,15 @@
     "librarian": "anthropic/claude-sonnet-4-5-thinking",
     "frontend": "google/gemini-2.5-pro",
     "documentWriter": "anthropic/claude-opus-4-5",
-    "multimodalLooker": "google/gemini-2.5-pro"
+    "multimodalLooker": "google/gemini-2.5-pro",
+    "settings": {
+      "sisyphus": { "thinkingLevel": "high" },
+      "oracle": { "thinkingLevel": "high" },
+      "librarian": { "thinkingLevel": "medium" },
+      "frontend": { "temperature": 0.5 },
+      "documentWriter": { "temperature": 0.4 },
+      "multimodalLooker": { "temperature": 0.2 }
+    }
   },
   "bmad": {
     "defaultTrack": "enterprise",

package/config/presets/minimal.json

@@ -5,12 +5,18 @@
   "subscriptions": {
     "claude": { "enabled": true, "tier": "pro" },
     "openai": { "enabled": false },
-    "google": { "enabled": false, "authMethod": "none" }
+    "google": { "enabled": false, "authMethod": "none" },
+    "githubCopilot": { "enabled": false, "plan": "none" }
   },
   "models": {
     "sisyphus": "anthropic/claude-sonnet-4-5",
     "oracle": "anthropic/claude-sonnet-4-5",
-    "librarian": "anthropic/claude-sonnet-4-5"
+    "librarian": "anthropic/claude-sonnet-4-5",
+    "settings": {
+      "sisyphus": { "temperature": 0.2 },
+      "oracle": { "temperature": 0.1 },
+      "librarian": { "temperature": 0.3 }
+    }
   },
   "bmad": {
     "defaultTrack": "quick-flow",

package/config/presets/solo-quick.json

@@ -5,12 +5,18 @@
   "subscriptions": {
     "claude": { "enabled": true, "tier": "max5x" },
     "openai": { "enabled": false },
-    "google": { "enabled": false, "authMethod": "none" }
+    "google": { "enabled": false, "authMethod": "none" },
+    "githubCopilot": { "enabled": false, "plan": "none" }
   },
   "models": {
     "sisyphus": "anthropic/claude-sonnet-4-5-thinking",
     "oracle": "anthropic/claude-sonnet-4-5-thinking",
-    "librarian": "anthropic/claude-sonnet-4-5"
+    "librarian": "anthropic/claude-sonnet-4-5",
+    "settings": {
+      "sisyphus": { "thinkingLevel": "medium" },
+      "oracle": { "thinkingLevel": "high" },
+      "librarian": { "temperature": 0.3 }
+    }
   },
   "bmad": {
     "defaultTrack": "quick-flow",

package/config/presets/standard.json

@@ -5,7 +5,8 @@
   "subscriptions": {
     "claude": { "enabled": true, "tier": "max5x" },
     "openai": { "enabled": true },
-    "google": { "enabled": true, "authMethod": "antigravity" }
+    "google": { "enabled": true, "authMethod": "antigravity" },
+    "githubCopilot": { "enabled": false, "plan": "none" }
   },
   "models": {
     "sisyphus": "anthropic/claude-sonnet-4-5-thinking",
@@ -13,7 +14,15 @@
     "librarian": "anthropic/claude-sonnet-4-5",
     "frontend": "anthropic/claude-sonnet-4-5",
     "documentWriter": "google/gemini-2.5-pro",
-    "multimodalLooker": "google/gemini-2.5-flash"
+    "multimodalLooker": "google/gemini-2.5-flash",
+    "settings": {
+      "sisyphus": { "thinkingLevel": "medium" },
+      "oracle": { "thinkingLevel": "high" },
+      "librarian": { "thinkingLevel": "low" },
+      "frontend": { "temperature": 0.5 },
+      "documentWriter": { "temperature": 0.4 },
+      "multimodalLooker": { "temperature": 0.2 }
+    }
   },
   "bmad": {
     "defaultTrack": "bmad-method",