release: v3.0.1

All documentation, agent prompts, and skill descriptions were still
referencing the old 'skills' parameter name for delegate_task, but the
tool implementation requires 'load_skills' (renamed in commit aa2b052).
This caused confusion and errors for users following the docs.

Fixes #1008

Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>

.opencode/command/remove-deadcode.md

@@ -0,0 +1,342 @@
+---
+description: Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits
+---
+
+<command-instruction>
+You are a dead code removal specialist. Execute the FULL dead code removal workflow using ultrawork mode.
+
+Your core weapon: **LSP FindReferences**. If a symbol has ZERO external references, it's dead. Remove it.
+
+## CRITICAL RULES
+
+1. **LSP is law.** Never guess. Always verify with `LspFindReferences` before removing ANYTHING.
+2. **One removal = one commit.** Every dead code removal gets its own atomic commit.
+3. **Test after every removal.** Run `bun test` after each. If it fails, REVERT and skip.
+4. **Leaf-first order.** Remove deepest unused symbols first, then work up the dependency chain. Removing a leaf may expose new dead code upstream.
+5. **Never remove entry points.** `src/index.ts`, `src/cli/index.ts`, test files, config files, and files in `packages/` are off-limits unless explicitly targeted.
+
+---
+
+## STEP 0: REGISTER TODO LIST (MANDATORY FIRST ACTION)
+
+```
+TodoWrite([
+  {"id": "scan", "content": "PHASE 1: Scan codebase for dead code candidates using LSP + explore agents", "status": "pending", "priority": "high"},
+  {"id": "verify", "content": "PHASE 2: Verify each candidate with LspFindReferences - zero false positives", "status": "pending", "priority": "high"},
+  {"id": "plan", "content": "PHASE 3: Plan removal order (leaf-first dependency order)", "status": "pending", "priority": "high"},
+  {"id": "remove", "content": "PHASE 4: Remove dead code one-by-one (remove -> test -> commit loop)", "status": "pending", "priority": "high"},
+  {"id": "final", "content": "PHASE 5: Final verification - full test suite + build + typecheck", "status": "pending", "priority": "high"}
+])
+```
+
+---
+
+## PHASE 1: SCAN FOR DEAD CODE CANDIDATES
+
+**Mark scan as in_progress.**
+
+### 1.1: Launch Parallel Explore Agents (ALL BACKGROUND)
+
+Fire ALL simultaneously:
+
+```
+// Agent 1: Find all exported symbols
+delegate_task(subagent_type="explore", run_in_background=true,
+  prompt="Find ALL exported functions, classes, types, interfaces, and constants across src/.
+  List each with: file path, line number, symbol name, export type (named/default).
+  EXCLUDE: src/index.ts root exports, test files.
+  Return as structured list.")
+
+// Agent 2: Find potentially unused files
+delegate_task(subagent_type="explore", run_in_background=true,
+  prompt="Find files in src/ that are NOT imported by any other file.
+  Check import/require statements across the entire codebase.
+  EXCLUDE: index.ts files, test files, entry points, config files, .md files.
+  Return list of potentially orphaned files.")
+
+// Agent 3: Find unused imports within files
+delegate_task(subagent_type="explore", run_in_background=true,
+  prompt="Find unused imports across src/**/*.ts files.
+  Look for import statements where the imported symbol is never referenced in the file body.
+  Return: file path, line number, imported symbol name.")
+
+// Agent 4: Find functions/variables only used in their own declaration
+delegate_task(subagent_type="explore", run_in_background=true,
+  prompt="Find private/non-exported functions, variables, and types in src/**/*.ts that appear
+  to have zero usage beyond their declaration. Return: file path, line number, symbol name.")
+```
+
+### 1.2: Direct AST-Grep Scans (WHILE AGENTS RUN)
+
+```typescript
+// Find unused imports pattern
+ast_grep_search(pattern="import { $NAME } from '$PATH'", lang="typescript", paths=["src/"])
+
+// Find empty export objects
+ast_grep_search(pattern="export {}", lang="typescript", paths=["src/"])
+```
+
+### 1.3: Collect All Results
+
+Collect background agent results. Compile into a master candidate list:
+
+```
+## DEAD CODE CANDIDATES
+
+| # | File | Line | Symbol | Type | Confidence |
+|---|------|------|--------|------|------------|
+| 1 | src/foo.ts | 42 | unusedFunc | function | HIGH |
+| 2 | src/bar.ts | 10 | OldType | type | MEDIUM |
+```
+
+**Mark scan as completed.**
+
+---
+
+## PHASE 2: VERIFY WITH LSP (ZERO FALSE POSITIVES)
+
+**Mark verify as in_progress.**
+
+For EVERY candidate from Phase 1, run this verification:
+
+### 2.1: The LSP Verification Protocol
+
+For each candidate symbol:
+
+```typescript
+// Step 1: Find the symbol's exact position
+LspDocumentSymbols(filePath)  // Get line/character of the symbol
+
+// Step 2: Find ALL references across the ENTIRE workspace
+LspFindReferences(filePath, line, character, includeDeclaration=false)
+// includeDeclaration=false → only counts USAGES, not the definition itself
+
+// Step 3: Evaluate
+// 0 references → CONFIRMED DEAD CODE
+// 1+ references → NOT dead, remove from candidate list
+```
+
+### 2.2: False Positive Guards
+
+**NEVER mark as dead code if:**
+- Symbol is in `src/index.ts` (package entry point)
+- Symbol is in any `index.ts` that re-exports (barrel file check: look if it's re-exported)
+- Symbol is referenced in test files (tests are valid consumers)
+- Symbol has `@public` or `@api` JSDoc tags
+- Symbol is in a file listed in `package.json` exports
+- Symbol is a hook factory (`createXXXHook`) registered in `src/index.ts`
+- Symbol is a tool factory (`createXXXTool`) registered in tool loading
+- Symbol is an agent definition registered in `agentSources`
+- File is a command template, skill definition, or MCP config
+
+### 2.3: Build Confirmed Dead Code List
+
+After verification, produce:
+
+```
+## CONFIRMED DEAD CODE (LSP-verified, 0 external references)
+
+| # | File | Line | Symbol | Type | Safe to Remove |
+|---|------|------|--------|------|----------------|
+| 1 | src/foo.ts | 42 | unusedFunc | function | YES |
+```
+
+**If ZERO confirmed dead code found: Report "No dead code found" and STOP.**
+
+**Mark verify as completed.**
+
+---
+
+## PHASE 3: PLAN REMOVAL ORDER
+
+**Mark plan as in_progress.**
+
+### 3.1: Dependency Analysis
+
+For each confirmed dead symbol:
+1. Check if removing it would expose other dead code
+2. Check if other dead symbols depend on this one
+3. Build removal dependency graph
+
+### 3.2: Order by Leaf-First
+
+```
+Removal Order:
+1. [Leaf symbols - no other dead code depends on them]
+2. [Intermediate symbols - depended on only by already-removed dead code]
+3. [Dead files - entire files with no live exports]
+```
+
+### 3.3: Register Granular Todos
+
+Create one todo per removal:
+
+```
+TodoWrite([
+  {"id": "remove-1", "content": "Remove unusedFunc from src/foo.ts:42", "status": "pending", "priority": "high"},
+  {"id": "remove-2", "content": "Remove OldType from src/bar.ts:10", "status": "pending", "priority": "high"},
+  // ... one per confirmed dead symbol
+])
+```
+
+**Mark plan as completed.**
+
+---
+
+## PHASE 4: ITERATIVE REMOVAL LOOP
+
+**Mark remove as in_progress.**
+
+For EACH dead code item, execute this exact loop:
+
+### 4.1: Pre-Removal Check
+
+```typescript
+// Re-verify it's still dead (previous removals may have changed things)
+LspFindReferences(filePath, line, character, includeDeclaration=false)
+// If references > 0 now → SKIP (previous removal exposed a new consumer)
+```
+
+### 4.2: Remove the Dead Code
+
+Use appropriate tool:
+
+**For unused imports:**
+```typescript
+Edit(filePath, oldString="import { deadSymbol } from '...';\n", newString="")
+// Or if it's one of many imports, remove just the symbol from the import list
+```
+
+**For unused functions/classes/types:**
+```typescript
+// Read the full symbol extent first
+Read(filePath, offset=startLine, limit=endLine-startLine+1)
+// Then remove it
+Edit(filePath, oldString="[full symbol text]", newString="")
+```
+
+**For dead files:**
+```bash
+# Only after confirming ZERO imports point to this file
+rm "path/to/dead-file.ts"
+```
+
+**After removal, also clean up:**
+- Remove any imports that were ONLY used by the removed code
+- Remove any now-empty import statements
+- Fix any trailing whitespace / double blank lines left behind
+
+### 4.3: Post-Removal Verification
+
+```typescript
+// 1. LSP diagnostics on changed file
+LspDiagnostics(filePath, severity="error")
+// Must be clean (or only pre-existing errors)
+
+// 2. Run tests
+bash("bun test")
+// Must pass
+
+// 3. Typecheck
+bash("bun run typecheck")
+// Must pass
+```
+
+### 4.4: Handle Failures
+
+If ANY verification fails:
+1. **REVERT** the change immediately (`git checkout -- [file]`)
+2. Mark this removal todo as `cancelled` with note: "Removal caused [error]. Skipped."
+3. Proceed to next item
+
+### 4.5: Commit
+
+```bash
+git add [changed-files]
+git commit -m "refactor: remove unused [symbolType] [symbolName] from [filePath]"
+```
+
+Mark this removal todo as `completed`.
+
+### 4.6: Re-scan After Removal
+
+After removing a symbol, check if its removal exposed NEW dead code:
+- Were there imports that only existed to serve the removed symbol?
+- Are there other symbols in the same file now unreferenced?
+
+If new dead code is found, add it to the removal queue.
+
+**Repeat 4.1-4.6 for every item. Mark remove as completed when done.**
+
+---
+
+## PHASE 5: FINAL VERIFICATION
+
+**Mark final as in_progress.**
+
+### 5.1: Full Test Suite
+```bash
+bun test
+```
+
+### 5.2: Full Typecheck
+```bash
+bun run typecheck
+```
+
+### 5.3: Full Build
+```bash
+bun run build
+```
+
+### 5.4: Summary Report
+
+```markdown
+## Dead Code Removal Complete
+
+### Removed
+| # | Symbol | File | Type | Commit |
+|---|--------|------|------|--------|
+| 1 | unusedFunc | src/foo.ts | function | abc1234 |
+
+### Skipped (caused failures)
+| # | Symbol | File | Reason |
+|---|--------|------|--------|
+| 1 | riskyFunc | src/bar.ts | Test failure: [details] |
+
+### Verification
+- Tests: PASSED (X/Y passing)
+- Typecheck: CLEAN
+- Build: SUCCESS
+- Total dead code removed: N symbols across M files
+- Total commits: K atomic commits
+```
+
+**Mark final as completed.**
+
+---
+
+## SCOPE CONTROL
+
+**If $ARGUMENTS is provided**, narrow the scan to the specified scope:
+- File path: Only scan that file
+- Directory: Only scan that directory
+- Symbol name: Only check that specific symbol
+- "all" or empty: Full project scan (default)
+
+## ABORT CONDITIONS
+
+**STOP and report to user if:**
+- 3 consecutive removals cause test failures
+- Build breaks and cannot be fixed by reverting
+- More than 50 candidates found (ask user to narrow scope)
+
+## LANGUAGE
+
+Use English for commit messages and technical output.
+
+</command-instruction>
+
+<user-request>
+$ARGUMENTS
+</user-request>

AGENTS.md

@@ -1,7 +1,7 @@
 # PROJECT KNOWLEDGE BASE
 
-**Generated:** 2026-01-23T15:59:00+09:00
-**Commit:** 599fad0e
+**Generated:** 2026-01-25T13:10:00+09:00
+**Commit:** 043b1a33
 **Branch:** dev
 
 ## OVERVIEW
@@ -21,7 +21,7 @@ oh-my-opencode/
 │   ├── cli/           # CLI installer, doctor - see src/cli/AGENTS.md
 │   ├── mcp/           # Built-in MCPs - see src/mcp/AGENTS.md
 │   ├── config/        # Zod schema, TypeScript types
-│   └── index.ts       # Main plugin entry (593 lines)
+│   └── index.ts       # Main plugin entry (601 lines)
 ├── script/            # build-schema.ts, build-binaries.ts
 ├── packages/          # 7 platform-specific binaries
 └── dist/              # Build output (ESM + .d.ts)
@@ -36,6 +36,7 @@ oh-my-opencode/
 | Add tool | `src/tools/` | Dir with index/types/constants/tools.ts |
 | Add MCP | `src/mcp/` | Create config, add to index.ts |
 | Add skill | `src/features/builtin-skills/` | Create dir with SKILL.md |
+| Add command | `src/features/builtin-commands/` | Add template + register in commands.ts |
 | Config schema | `src/config/schema.ts` | Zod schema, run `bun run build:schema` |
 | Background agents | `src/features/background-agent/` | manager.ts (1335 lines) |
 | Orchestrator | `src/hooks/atlas/` | Main orchestration hook (773 lines) |
@@ -60,7 +61,7 @@ oh-my-opencode/
 - **Build**: `bun build` (ESM) + `tsc --emitDeclarationOnly`
 - **Exports**: Barrel pattern via index.ts
 - **Naming**: kebab-case dirs, `createXXXHook`/`createXXXTool` factories
-- **Testing**: BDD comments, 90 test files
+- **Testing**: BDD comments, 95 test files
 - **Temperature**: 0.1 for code agents, max 0.3
 
 ## ANTI-PATTERNS
@@ -99,7 +100,7 @@ oh-my-opencode/
 bun run typecheck      # Type check
 bun run build          # ESM + declarations + schema
 bun run rebuild        # Clean + Build
-bun test               # 90 test files
+bun test               # 95 test files
 ```
 
 ## DEPLOYMENT
@@ -118,7 +119,11 @@ bun test               # 90 test files
 | `src/agents/prometheus-prompt.ts` | 1196 | Planning agent |
 | `src/tools/delegate-task/tools.ts` | 1039 | Category-based delegation |
 | `src/hooks/atlas/index.ts` | 773 | Orchestrator hook |
-| `src/cli/config-manager.ts` | 641 | JSONC config parsing |
+| `src/cli/config-manager.ts` | 664 | JSONC config parsing |
+| `src/features/builtin-commands/templates/refactor.ts` | 619 | Refactor command template |
+| `src/index.ts` | 601 | Main plugin entry |
+| `src/tools/lsp/client.ts` | 596 | LSP JSON-RPC client |
+| `src/agents/atlas.ts` | 572 | Atlas orchestrator agent |
 
 ## MCP ARCHITECTURE
 

bun.lock

@@ -27,13 +27,13 @@
         "typescript": "^5.7.3",
       },
       "optionalDependencies": {
-        "oh-my-opencode-darwin-arm64": "3.0.0-beta.16",
-        "oh-my-opencode-darwin-x64": "3.0.0-beta.16",
-        "oh-my-opencode-linux-arm64": "3.0.0-beta.16",
-        "oh-my-opencode-linux-arm64-musl": "3.0.0-beta.16",
-        "oh-my-opencode-linux-x64": "3.0.0-beta.16",
-        "oh-my-opencode-linux-x64-musl": "3.0.0-beta.16",
-        "oh-my-opencode-windows-x64": "3.0.0-beta.16",
+        "oh-my-opencode-darwin-arm64": "3.0.0",
+        "oh-my-opencode-darwin-x64": "3.0.0",
+        "oh-my-opencode-linux-arm64": "3.0.0",
+        "oh-my-opencode-linux-arm64-musl": "3.0.0",
+        "oh-my-opencode-linux-x64": "3.0.0",
+        "oh-my-opencode-linux-x64-musl": "3.0.0",
+        "oh-my-opencode-windows-x64": "3.0.0",
       },
     },
   },
@@ -225,19 +225,19 @@
 
     "object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],
 
-    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.0.0-beta.16", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-1gfnTsKpYxTMXpbuV98wProR3RMe6BI/muuSVa3Xy68EEkBJsuRAne6IzFq/yxIMbx9OiQaS5cTE0mxFtxcCGA=="],
+    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.0.0", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-zelvb7qz5GsS+Dhyz9rACZrkUMtWbAZGijiHSQqmRcjlN/sRPNhXtsL55VheDjlPM3VP+t3+psv+se0WA/aw5w=="],
 
-    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.0.0-beta.16", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-/h7kBZAN5Ut9kL7gEtwVVZ49Kw4gZoSVJdrpnh7Wij0a3mlOwqbkgGilK7oUiJ2N8fsxvxEBbTscYOLAdhyVBw=="],
+    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.0.0", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-dRMD1U5zIrb6BsiKQJZtAFtuD8clAQquZyU2LajMoFTHBNhcBDIgsaBBwvMBIq7dTe8rnFq91ExiFA8OfdrzBA=="],
 
-    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.0.0-beta.16", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-jW7pl76WerBa7FucKCYcthpbKbhJQSVe6rqUFSbVobjOP9VWslrGdxc9Y8BeiMx9SJEFYwA8/2ROhnOHpH3TxA=="],
+    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.0.0", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-Wx6Cx2Nu2T69mfZa3FQ3gk0OFONvMh48rMVYK0Cp8VX5W4Zb/GZgTUFmZlYsApyxqP+7J9m18skd46qPOhzuEQ=="],
 
-    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.0.0-beta.16", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-cXXka0zQDBiFu9mmxa45o3g812w8q/jZRYgdwJsLbj3nm24WXv6uRP7nnVVoZiVmJ2GQbLE1nyGCMkBXFwRGGA=="],
+    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.0.0", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-mfOlptgLoXLVuhFRcXgZU7BYGuL1axZOMOOjONgncNzOp/BQYU5B9BRFihBUXdDsWGmeMiLowrYGBhVpSv3NlA=="],
 
-    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.0.0-beta.16", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-4VS1V6DiXdWHQ/AGc3rB1sCxFUlD1REex0Ai/y4tEgA2M0FD0Bu+tjXHhDghUvC8f0kQBRfijnTrtc1Lh7hIrA=="],
+    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.0.0", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-vVjshfaz0UC9NrGD9FfjlYK5NvckIW0sZaE/wRv/LKjrukHFH1jJpJa5KKXxBWLsEJjt6ooJRguXXxtfNXpAWw=="],
 
-    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.0.0-beta.16", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-PGVe7vyUK3hjSNfvu1fBXTbgbe0OPh7JgB/TZR2U5R54X1k3NBkb1VHX9yxEUSA0VsNR+inE2x+DfEA+7KIruQ=="],
+    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.0.0", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-N6cNJ7+Dj0a5dWqPf6OKfB39o8HWw5HQ3hB4omgYqc6Gzo6nChA4KIiVefEC3+tIL98x4XvMeD7OU+UYgwxHnQ=="],
 
-    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.0.0-beta.16", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-1lN/8y4laQnSJDvyARuV5YaETAwBb+PK06QHQzpoK/0asiFoEIBcKNgjaRwau+nBsdRUrQocE2xc6g2ZNH4HUw=="],
+    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.0.0", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-TaC0hiHpnsS42GWTVUKoTwCb+QzNLBlQtTkIQ0PjlkDYFjlEC2LuR2FFcscik055PRRIGishyB9A1n/8XAgcvA=="],
 
     "on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],
 

docs/category-skill-guide.md

@@ -70,12 +70,12 @@ A Skill is a mechanism that injects **specialized knowledge (Context)** and **to
 
 ### Usage
 
-Add desired skill names to the `skills` array.
+Add desired skill names to the `load_skills` array.
 
 ```typescript
 delegate_task(
   category="quick",
-  skills=["git-master"],
+  load_skills=["git-master"],
   prompt="Commit current changes. Follow commit message style."
 )
 ```
@@ -110,17 +110,17 @@ You can create powerful specialized agents by combining Categories and Skills.
 
 ### 🎨 The Designer (UI Implementation)
 - **Category**: `visual-engineering`
-- **Skills**: `["frontend-ui-ux", "playwright"]`
+- **load_skills**: `["frontend-ui-ux", "playwright"]`
 - **Effect**: Implements aesthetic UI and verifies rendering results directly in browser.
 
 ### 🏗️ The Architect (Design Review)
 - **Category**: `ultrabrain`
-- **Skills**: `[]` (pure reasoning)
+- **load_skills**: `[]` (pure reasoning)
 - **Effect**: Leverages GPT-5.2's logical reasoning for in-depth system architecture analysis.
 
 ### ⚡ The Maintainer (Quick Fixes)
 - **Category**: `quick`
-- **Skills**: `["git-master"]`
+- **load_skills**: `["git-master"]`
 - **Effect**: Uses cost-effective models to quickly fix code and generate clean commits.
 
 ---
@@ -131,7 +131,7 @@ When delegating, **clear and specific** prompts are essential. Include these 7 e
 
 1. **TASK**: What needs to be done? (single objective)
 2. **EXPECTED OUTCOME**: What is the deliverable?
-3. **REQUIRED SKILLS**: Which skills should be used?
+3. **REQUIRED SKILLS**: Which skills should be loaded via `load_skills`?
 4. **REQUIRED TOOLS**: Which tools must be used? (whitelist)
 5. **MUST DO**: What must be done (constraints)
 6. **MUST NOT DO**: What must never be done

docs/configurations.md

@@ -83,7 +83,7 @@ When both `oh-my-opencode.jsonc` and `oh-my-opencode.json` files exist, `.jsonc`
 
 ## Google Auth
 
-**Recommended**: For Google Gemini authentication, install the [`opencode-antigravity-auth`](https://github.com/NoeFabris/opencode-antigravity-auth) plugin. It provides multi-account load balancing, more models (including Claude via Antigravity), and active maintenance. See [Installation > Google Gemini](../README.md#google-gemini-antigravity-oauth).
+**Recommended**: For Google Gemini authentication, install the [`opencode-antigravity-auth`](https://github.com/NoeFabris/opencode-antigravity-auth) plugin (`@latest`). It provides multi-account load balancing, variant-based thinking levels, dual quota system (Antigravity + Gemini CLI), and active maintenance. See [Installation > Google Gemini](docs/guide/installation.md#google-gemini-antigravity-oauth).
 
 ## Agents
 
@@ -160,7 +160,7 @@ Available agents: `oracle`, `librarian`, `explore`, `multimodal-looker`
 Oh My OpenCode includes built-in skills that provide additional capabilities:
 
 - **playwright**: Browser automation with Playwright MCP. Use for web scraping, testing, screenshots, and browser interactions.
-- **git-master**: Git expert for atomic commits, rebase/squash, and history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with `delegate_task(category='quick', skills=['git-master'], ...)` to save context.
+- **git-master**: Git expert for atomic commits, rebase/squash, and history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with `delegate_task(category='quick', load_skills=['git-master'], ...)` to save context.
 
 Disable built-in skills via `disabled_skills` in `~/.config/opencode/oh-my-opencode.json` or `.opencode/oh-my-opencode.json`:
 
@@ -404,7 +404,7 @@ Each agent has a defined provider priority chain. The system tries providers in
 | **Sisyphus** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
 | **oracle** | `gpt-5.2` | openai → anthropic → google → github-copilot → opencode |
 | **librarian** | `big-pickle` | opencode → github-copilot → anthropic |
-| **explore** | `gpt-5-nano` | opencode → anthropic → github-copilot |
+| **explore** | `gpt-5-nano` | anthropic → opencode |
 | **multimodal-looker** | `gemini-3-flash` | google → openai → zai-coding-plan → anthropic → opencode |
 | **Prometheus (Planner)** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
 | **Metis (Plan Consultant)** | `claude-sonnet-4-5` | anthropic → github-copilot → opencode → antigravity → google |

docs/guide/installation.md

@@ -132,7 +132,7 @@ First, add the opencode-antigravity-auth plugin:
 {
   "plugin": [
     "oh-my-opencode",
-    "opencode-antigravity-auth@1.2.8"
+    "opencode-antigravity-auth@latest"
   ]
 }
 ```
@@ -140,7 +140,7 @@ First, add the opencode-antigravity-auth plugin:
 ##### Model Configuration
 
 You'll also need full model settings in `opencode.json`.
-Read the [opencode-antigravity-auth documentation](https://github.com/NoeFabris/opencode-antigravity-auth), copy provider/models config from the README, and merge carefully to avoid breaking the user's existing setup.
+Read the [opencode-antigravity-auth documentation](https://github.com/NoeFabris/opencode-antigravity-auth), copy the full model configuration from the README, and merge carefully to avoid breaking the user's existing setup. The plugin now uses a **variant system** — models like `antigravity-gemini-3-pro` support `low`/`high` variants instead of separate `-low`/`-high` model entries.
 
 ##### oh-my-opencode Agent Model Override
 
@@ -154,7 +154,17 @@ The `opencode-antigravity-auth` plugin uses different model names than the built
 }
 ```
 
-**Available model names**: `google/antigravity-gemini-3-pro-high`, `google/antigravity-gemini-3-pro-low`, `google/antigravity-gemini-3-flash`, `google/antigravity-claude-sonnet-4-5`, `google/antigravity-claude-sonnet-4-5-thinking-low`, `google/antigravity-claude-sonnet-4-5-thinking-medium`, `google/antigravity-claude-sonnet-4-5-thinking-high`, `google/antigravity-claude-opus-4-5-thinking-low`, `google/antigravity-claude-opus-4-5-thinking-medium`, `google/antigravity-claude-opus-4-5-thinking-high`, `google/gemini-3-pro`, `google/gemini-3-flash`, `google/gemini-2.5-pro`, `google/gemini-2.5-flash`
+**Available models (Antigravity quota)**:
+- `google/antigravity-gemini-3-pro` — variants: `low`, `high`
+- `google/antigravity-gemini-3-flash` — variants: `minimal`, `low`, `medium`, `high`
+- `google/antigravity-claude-sonnet-4-5` — no variants
+- `google/antigravity-claude-sonnet-4-5-thinking` — variants: `low`, `max`
+- `google/antigravity-claude-opus-4-5-thinking` — variants: `low`, `max`
+
+**Available models (Gemini CLI quota)**:
+- `google/gemini-2.5-flash`, `google/gemini-2.5-pro`, `google/gemini-3-flash-preview`, `google/gemini-3-pro-preview`
+
+> **Note**: Legacy tier-suffixed names like `google/antigravity-gemini-3-pro-high` still work but variants are recommended. Use `--variant=high` with the base model name instead.
 
 Then authenticate:
 
@@ -183,7 +193,7 @@ When GitHub Copilot is the best available provider, oh-my-opencode uses these mo
 | ------------- | -------------------------------- |
 | **Sisyphus**  | `github-copilot/claude-opus-4.5` |
 | **Oracle**    | `github-copilot/gpt-5.2`         |
-| **Explore**   | `github-copilot/gpt-5-nano-fast-1`|
+| **Explore**   | `opencode/gpt-5-nano`              |
 | **Librarian** | `zai-coding-plan/glm-4.7` (if Z.ai available) or fallback |
 
 GitHub Copilot acts as a proxy provider, routing requests to underlying models based on your subscription.

docs/guide/overview.md

@@ -128,7 +128,7 @@ Here's a real-world config for a user with **Claude, OpenAI, Gemini, and Z.ai**
   "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
   "agents": {
     // Override specific agents only - rest use fallback chain
-    "Atlas": { "model": "anthropic/claude-sonnet-4-5", "variant": "max" },
+    "atlas": { "model": "anthropic/claude-sonnet-4-5", "variant": "max" },
     "librarian": { "model": "zai-coding-plan/glm-4.7" },
     "explore": { "model": "opencode/gpt-5-nano" },
     "multimodal-looker": { "model": "zai-coding-plan/glm-4.6v" }

docs/guide/understanding-orchestration-system.md

@@ -326,13 +326,13 @@ Skills prepend specialized instructions to subagent prompts:
 // Category + Skill combination
 delegate_task(
   category="visual-engineering", 
-  skills=["frontend-ui-ux"],  // Adds UI/UX expertise
+  load_skills=["frontend-ui-ux"],  // Adds UI/UX expertise
   prompt="..."
 )
 
 delegate_task(
   category="general",
-  skills=["playwright"],  // Adds browser automation expertise
+  load_skills=["playwright"],  // Adds browser automation expertise
   prompt="..."
 )
 ```
@@ -341,8 +341,8 @@ delegate_task(
 
 | Before | After |
 |--------|-------|
-| Hardcoded: `frontend-ui-ux-engineer` (Gemini 3 Pro) | `category="visual-engineering" + skills=["frontend-ui-ux"]` |
-| One-size-fits-all | `category="visual-engineering" + skills=["unity-master"]` |
+| Hardcoded: `frontend-ui-ux-engineer` (Gemini 3 Pro) | `category="visual-engineering" + load_skills=["frontend-ui-ux"]` |
+| One-size-fits-all | `category="visual-engineering" + load_skills=["unity-master"]` |
 | Model bias | Category-based: model abstraction eliminates bias |
 
 ---
@@ -365,7 +365,7 @@ sequenceDiagram
         
         Note over Orchestrator: Prompt Structure:<br/>1. TASK (exact checkbox)<br/>2. EXPECTED OUTCOME<br/>3. REQUIRED SKILLS<br/>4. REQUIRED TOOLS<br/>5. MUST DO<br/>6. MUST NOT DO<br/>7. CONTEXT + Wisdom
         
-        Orchestrator->>Junior: delegate_task(category, skills, prompt)
+        Orchestrator->>Junior: delegate_task(category, load_skills, prompt)
         
         Junior->>Junior: Create todos, execute
         Junior->>Junior: Verify (lsp_diagnostics, tests)

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -73,13 +73,13 @@
     "typescript": "^5.7.3"
   },
   "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "3.0.0",
-    "oh-my-opencode-darwin-x64": "3.0.0",
-    "oh-my-opencode-linux-arm64": "3.0.0",
-    "oh-my-opencode-linux-arm64-musl": "3.0.0",
-    "oh-my-opencode-linux-x64": "3.0.0",
-    "oh-my-opencode-linux-x64-musl": "3.0.0",
-    "oh-my-opencode-windows-x64": "3.0.0"
+    "oh-my-opencode-darwin-arm64": "3.0.1",
+    "oh-my-opencode-darwin-x64": "3.0.1",
+    "oh-my-opencode-linux-arm64": "3.0.1",
+    "oh-my-opencode-linux-arm64-musl": "3.0.1",
+    "oh-my-opencode-linux-x64": "3.0.1",
+    "oh-my-opencode-linux-x64-musl": "3.0.1",
+    "oh-my-opencode-windows-x64": "3.0.1"
   },
   "trustedDependencies": [
     "@ast-grep/cli",

packages/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-arm64",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (darwin-x64)",
   "license": "MIT",
   "repository": {

packages/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64-musl",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
   "license": "MIT",
   "repository": {

signatures/cla.json

@@ -767,6 +767,54 @@
       "created_at": "2026-01-24T04:41:46Z",
       "repoId": 1108837393,
       "pullRequestNo": 1042
+    },
+    {
+      "name": "AamiRobin",
+      "id": 22963668,
+      "comment_id": 3794632200,
+      "created_at": "2026-01-24T13:28:22Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1067
+    },
+    {
+      "name": "ThanhNguyxn",
+      "id": 74597207,
+      "comment_id": 3795232176,
+      "created_at": "2026-01-24T17:41:53Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1075
+    },
+    {
+      "name": "sadnow",
+      "id": 87896100,
+      "comment_id": 3795495342,
+      "created_at": "2026-01-24T20:49:29Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1080
+    },
+    {
+      "name": "jsl9208",
+      "id": 4048787,
+      "comment_id": 3795582626,
+      "created_at": "2026-01-24T21:41:24Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1082
+    },
+    {
+      "name": "potb",
+      "id": 10779093,
+      "comment_id": 3795856573,
+      "created_at": "2026-01-25T02:38:16Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1083
+    },
+    {
+      "name": "kvokka",
+      "id": 15954013,
+      "comment_id": 3795884358,
+      "created_at": "2026-01-25T03:13:52Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1084
     }
   ]
 }

sisyphus-prompt.md

@@ -239,7 +239,7 @@ Ask yourself:
 I will use delegate_task with:
 - **Category**: [selected-category-name]
 - **Why this category**: [how category description matches task domain]
-- **Skills**: [list of selected skills]
+- **load_skills**: [list of selected skills]
 - **Skill evaluation**:
   - [skill-1]: INCLUDED because [reason based on skill description]
   - [skill-2]: OMITTED because [reason why skill domain doesn't apply]
@@ -256,7 +256,7 @@ I will use delegate_task with:
 I will use delegate_task with:
 - **Category**: [category-name]
 - **Why this category**: Category description says "[quote description]" which matches this task's requirements
-- **Skills**: ["skill-a", "skill-b"]
+- **load_skills**: ["skill-a", "skill-b"]
 - **Skill evaluation**:
   - skill-a: INCLUDED - description says "[quote]" which applies to this task
   - skill-b: INCLUDED - description says "[quote]" which is needed here
@@ -265,7 +265,7 @@ I will use delegate_task with:
 
 delegate_task(
   category="[category-name]",
-  skills=["skill-a", "skill-b"],
+  load_skills=["skill-a", "skill-b"],
   prompt="..."
 )
 ```
@@ -276,12 +276,12 @@ delegate_task(
 I will use delegate_task with:
 - **Agent**: [agent-name]
 - **Reason**: This requires [agent's specialty] based on agent description
-- **Skills**: [] (agents have built-in expertise)
+- **load_skills**: [] (agents have built-in expertise)
 - **Expected Outcome**: [what agent should return]
 
 delegate_task(
   subagent_type="[agent-name]",
-  skills=[],
+  load_skills=[],
   prompt="..."
 )
 ```
@@ -292,13 +292,13 @@ delegate_task(
 I will use delegate_task with:
 - **Agent**: explore
 - **Reason**: Need to find all authentication implementations across the codebase - this is contextual grep
-- **Skills**: []
+- **load_skills**: []
 - **Expected Outcome**: List of files containing auth patterns
 
 delegate_task(
   subagent_type="explore",
   run_in_background=true,
-  skills=[],
+  load_skills=[],
   prompt="Find all authentication implementations in the codebase"
 )
 ```
@@ -306,7 +306,7 @@ delegate_task(
 **WRONG: No Skill Evaluation**
 
 ```
-delegate_task(category="...", skills=[], prompt="...")  // Where's the justification?
+delegate_task(category="...", load_skills=[], prompt="...")  // Where's the justification?
 ```
 
 **WRONG: Vague Category Selection**
@@ -329,11 +329,11 @@ I'll use this category because it seems right.
 ```typescript
 // CORRECT: Always background, always parallel
 // Contextual Grep (internal)
-delegate_task(subagent_type="explore", run_in_background=true, skills=[], prompt="Find auth implementations in our codebase...")
-delegate_task(subagent_type="explore", run_in_background=true, skills=[], prompt="Find error handling patterns here...")
+delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find auth implementations in our codebase...")
+delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find error handling patterns here...")
 // Reference Grep (external)
-delegate_task(subagent_type="librarian", run_in_background=true, skills=[], prompt="Find JWT best practices in official docs...")
-delegate_task(subagent_type="librarian", run_in_background=true, skills=[], prompt="Find how production apps handle auth in Express...")
+delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find JWT best practices in official docs...")
+delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find how production apps handle auth in Express...")
 // Continue working immediately. Collect with background_output when needed.
 
 // WRONG: Sequential or blocking
@@ -416,7 +416,7 @@ Skills inject specialized instructions into the subagent. Read the description t
 For EVERY skill listed above, ask yourself:
 > "Does this skill's expertise domain overlap with my task?"
 
-- If YES → INCLUDE in `skills=[...]`
+- If YES → INCLUDE in `load_skills=[...]`
 - If NO → You MUST justify why (see below)
 
 **STEP 3: Justify Omissions**
@@ -444,14 +444,14 @@ SKILL EVALUATION for "[skill-name]":
 ```typescript
 delegate_task(
   category="[selected-category]",
-  skills=["skill-1", "skill-2"],  // Include ALL relevant skills
+  load_skills=["skill-1", "skill-2"],  // Include ALL relevant skills
   prompt="..."
 )
 ```
 
 **ANTI-PATTERN (will produce poor results):**
 ```typescript
-delegate_task(category="...", skills=[], prompt="...")  // Empty skills without justification
+delegate_task(category="...", load_skills=[], prompt="...")  // Empty load_skills without justification
 ```
 ### Delegation Table:
 
@@ -724,7 +724,7 @@ If the user's approach seems problematic:
 | **Error Handling** | Empty catch blocks `catch(e) {}` |
 | **Testing** | Deleting failing tests to "pass" |
 | **Search** | Firing agents for single-line typos or obvious syntax errors |
-| **Delegation** | Using `skills=[]` without justifying why no skills apply |
+| **Delegation** | Using `load_skills=[]` without justifying why no skills apply |
 | **Debugging** | Shotgun debugging, random changes |
 ## Soft Guidelines
 

src/agents/AGENTS.md

@@ -8,17 +8,17 @@
 
 ```
 agents/
-├── atlas.ts                    # Master Orchestrator (543 lines)
-├── sisyphus.ts                 # Main prompt (615 lines)
-├── sisyphus-junior.ts          # Delegated task executor
-├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation
+├── atlas.ts                    # Master Orchestrator (572 lines)
+├── sisyphus.ts                 # Main prompt (450 lines)
+├── sisyphus-junior.ts          # Delegated task executor (135 lines)
+├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation (359 lines)
 ├── oracle.ts                   # Strategic advisor (GPT-5.2)
-├── librarian.ts                # Multi-repo research (GLM-4.7-free)
+├── librarian.ts                # Multi-repo research (326 lines)
 ├── explore.ts                  # Fast grep (Grok Code)
 ├── multimodal-looker.ts        # Media analyzer (Gemini 3 Flash)
 ├── prometheus-prompt.ts        # Planning (1196 lines)
-├── metis.ts                    # Plan consultant
-├── momus.ts                    # Plan reviewer
+├── metis.ts                    # Plan consultant (315 lines)
+├── momus.ts                    # Plan reviewer (444 lines)
 ├── types.ts                    # AgentModelConfig, AgentPromptMetadata
 ├── utils.ts                    # createBuiltinAgents(), resolveModelWithFallback()
 └── index.ts                    # builtinAgents export

src/agents/atlas.ts

@@ -58,7 +58,7 @@ Categories spawn \`Sisyphus-Junior-{category}\` with optimized settings:
 ${categoryRows.join("\n")}
 
 \`\`\`typescript
-delegate_task(category="[category-name]", skills=[...], prompt="...")
+delegate_task(category="[category-name]", load_skills=[...], prompt="...")
 \`\`\``
 }
 
@@ -84,12 +84,12 @@ ${skillRows.join("\n")}
 **MANDATORY: Evaluate ALL skills for relevance to your task.**
 
 Read each skill's description and ask: "Does this skill's domain overlap with my task?"
-- If YES: INCLUDE in skills=[...]
+- If YES: INCLUDE in load_skills=[...]
 - If NO: You MUST justify why in your pre-delegation declaration
 
 **Usage:**
 \`\`\`typescript
-delegate_task(category="[category]", skills=["skill-1", "skill-2"], prompt="...")
+delegate_task(category="[category]", load_skills=["skill-1", "skill-2"], prompt="...")
 \`\`\`
 
 **IMPORTANT:**
@@ -102,7 +102,7 @@ function buildDecisionMatrix(agents: AvailableAgent[], userCategories?: Record<s
   const allCategories = { ...DEFAULT_CATEGORIES, ...userCategories }
 
   const categoryRows = Object.entries(allCategories).map(([name]) =>
-    `| ${getCategoryDescription(name, userCategories)} | \`category="${name}", skills=[...]\` |`
+    `| ${getCategoryDescription(name, userCategories)} | \`category="${name}", load_skills=[...]\` |`
   )
 
   const agentRows = agents.map((a) => {
@@ -323,7 +323,7 @@ delegate_task(
 **If verification fails**: Resume the SAME session with the ACTUAL error output:
 \`\`\`typescript
 delegate_task(
-  resume="ses_xyz789",  // ALWAYS use the session from the failed task
+  session_id="ses_xyz789",  // ALWAYS use the session from the failed task
   load_skills=[...],
   prompt="Verification failed: {actual error}. Fix."
 )
@@ -331,24 +331,24 @@ delegate_task(
 
 ### 3.5 Handle Failures (USE RESUME)
 
-**CRITICAL: When re-delegating, ALWAYS use \`resume\` parameter.**
+**CRITICAL: When re-delegating, ALWAYS use \`session_id\` parameter.**
 
 Every \`delegate_task()\` output includes a session_id. STORE IT.
 
 If task fails:
 1. Identify what went wrong
 2. **Resume the SAME session** - subagent has full context already:
-   \`\`\`typescript
-   delegate_task(
-     resume="ses_xyz789",  // Session from failed task
-     load_skills=[...],
-     prompt="FAILED: {error}. Fix by: {specific instruction}"
-   )
-   \`\`\`
+    \`\`\`typescript
+    delegate_task(
+      session_id="ses_xyz789",  // Session from failed task
+      load_skills=[...],
+      prompt="FAILED: {error}. Fix by: {specific instruction}"
+    )
+    \`\`\`
 3. Maximum 3 retry attempts with the SAME session
 4. If blocked after 3 attempts: Document and continue to independent tasks
 
-**Why resume is MANDATORY for failures:**
+**Why session_id is MANDATORY for failures:**
 - Subagent already read all files, knows the context
 - No repeated exploration = 70%+ token savings
 - Subagent knows what approaches already failed
@@ -493,7 +493,7 @@ You are the QA gate. Subagents lie. Verify EVERYTHING.
 - Parallelize independent tasks
 - Verify with your own tools
 - **Store session_id from every delegation output**
-- **Use \`resume="{session_id}"\` for retries, fixes, and follow-ups**
+- **Use \`session_id="{session_id}"\` for retries, fixes, and follow-ups**
 </critical_overrides>
 `
 

src/agents/sisyphus.ts

@@ -144,11 +144,11 @@ ${librarianSection}
 \`\`\`typescript
 // CORRECT: Always background, always parallel
 // Contextual Grep (internal)
-delegate_task(subagent_type="explore", run_in_background=true, skills=[], prompt="Find auth implementations in our codebase...")
-delegate_task(subagent_type="explore", run_in_background=true, skills=[], prompt="Find error handling patterns here...")
+delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find auth implementations in our codebase...")
+delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find error handling patterns here...")
 // Reference Grep (external)
-delegate_task(subagent_type="librarian", run_in_background=true, skills=[], prompt="Find JWT best practices in official docs...")
-delegate_task(subagent_type="librarian", run_in_background=true, skills=[], prompt="Find how production apps handle auth in Express...")
+delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find JWT best practices in official docs...")
+delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find how production apps handle auth in Express...")
 // Continue working immediately. Collect with background_output when needed.
 
 // WRONG: Sequential or blocking
@@ -209,15 +209,15 @@ AFTER THE WORK YOU DELEGATED SEEMS DONE, ALWAYS VERIFY THE RESULTS AS FOLLOWING:
 
 Every \`delegate_task()\` output includes a session_id. **USE IT.**
 
-**ALWAYS resume when:**
+**ALWAYS continue when:**
 | Scenario | Action |
 |----------|--------|
-| Task failed/incomplete | \`resume="{session_id}", prompt="Fix: {specific error}"\` |
-| Follow-up question on result | \`resume="{session_id}", prompt="Also: {question}"\` |
-| Multi-turn with same agent | \`resume="{session_id}"\` - NEVER start fresh |
-| Verification failed | \`resume="{session_id}", prompt="Failed verification: {error}. Fix."\` |
+| Task failed/incomplete | \`session_id="{session_id}", prompt="Fix: {specific error}"\` |
+| Follow-up question on result | \`session_id="{session_id}", prompt="Also: {question}"\` |
+| Multi-turn with same agent | \`session_id="{session_id}"\` - NEVER start fresh |
+| Verification failed | \`session_id="{session_id}", prompt="Failed verification: {error}. Fix."\` |
 
-**Why resume is CRITICAL:**
+**Why session_id is CRITICAL:**
 - Subagent has FULL conversation context preserved
 - No repeated file reads, exploration, or setup
 - Saves 70%+ tokens on follow-ups
@@ -228,10 +228,10 @@ Every \`delegate_task()\` output includes a session_id. **USE IT.**
 delegate_task(category="quick", prompt="Fix the type error in auth.ts...")
 
 // CORRECT: Resume preserves everything
-delegate_task(resume="ses_abc123", prompt="Fix: Type error on line 42")
+delegate_task(session_id="ses_abc123", prompt="Fix: Type error on line 42")
 \`\`\`
 
-**After EVERY delegation, STORE the session_id for potential resume.**
+**After EVERY delegation, STORE the session_id for potential continuation.**
 
 ### Code Changes:
 - Match existing patterns (if codebase is disciplined)

src/cli/AGENTS.md

@@ -10,8 +10,9 @@ CLI entry: `bunx oh-my-opencode`. Interactive installer, doctor diagnostics. Com
 cli/
 ├── index.ts              # Commander.js entry
 ├── install.ts            # Interactive TUI (520 lines)
-├── config-manager.ts     # JSONC parsing (641 lines)
+├── config-manager.ts     # JSONC parsing (664 lines)
 ├── types.ts              # InstallArgs, InstallConfig
+├── model-fallback.ts     # Model fallback configuration
 ├── doctor/
 │   ├── index.ts          # Doctor entry
 │   ├── runner.ts         # Check orchestration
@@ -25,6 +26,7 @@ cli/
 │       ├── dependencies.ts # AST-Grep, Comment Checker
 │       ├── lsp.ts        # LSP connectivity
 │       ├── mcp.ts        # MCP validation
+│       ├── model-resolution.ts # Model resolution check
 │       └── gh.ts         # GitHub CLI
 ├── run/
 │   └── index.ts          # Session launcher

src/cli/config-manager.test.ts

@@ -170,7 +170,7 @@ describe("fetchNpmDistTags", () => {
 })
 
 describe("config-manager ANTIGRAVITY_PROVIDER_CONFIG", () => {
-  test("Gemini models include full spec (limit + modalities)", () => {
+  test("all models include full spec (limit + modalities + Antigravity label)", () => {
     const google = (ANTIGRAVITY_PROVIDER_CONFIG as any).google
     expect(google).toBeTruthy()
 
@@ -178,9 +178,11 @@ describe("config-manager ANTIGRAVITY_PROVIDER_CONFIG", () => {
     expect(models).toBeTruthy()
 
     const required = [
-      "antigravity-gemini-3-pro-high",
-      "antigravity-gemini-3-pro-low",
+      "antigravity-gemini-3-pro",
       "antigravity-gemini-3-flash",
+      "antigravity-claude-sonnet-4-5",
+      "antigravity-claude-sonnet-4-5-thinking",
+      "antigravity-claude-opus-4-5-thinking",
     ]
 
     for (const key of required) {
@@ -198,6 +200,43 @@ describe("config-manager ANTIGRAVITY_PROVIDER_CONFIG", () => {
       expect(Array.isArray(model.modalities.output)).toBe(true)
     }
   })
+
+  test("Gemini models have variant definitions", () => {
+    // #given the antigravity provider config
+    const models = (ANTIGRAVITY_PROVIDER_CONFIG as any).google.models as Record<string, any>
+
+    // #when checking Gemini Pro variants
+    const pro = models["antigravity-gemini-3-pro"]
+    // #then should have low and high variants
+    expect(pro.variants).toBeTruthy()
+    expect(pro.variants.low).toBeTruthy()
+    expect(pro.variants.high).toBeTruthy()
+
+    // #when checking Gemini Flash variants
+    const flash = models["antigravity-gemini-3-flash"]
+    // #then should have minimal, low, medium, high variants
+    expect(flash.variants).toBeTruthy()
+    expect(flash.variants.minimal).toBeTruthy()
+    expect(flash.variants.low).toBeTruthy()
+    expect(flash.variants.medium).toBeTruthy()
+    expect(flash.variants.high).toBeTruthy()
+  })
+
+  test("Claude thinking models have variant definitions", () => {
+    // #given the antigravity provider config
+    const models = (ANTIGRAVITY_PROVIDER_CONFIG as any).google.models as Record<string, any>
+
+    // #when checking Claude thinking variants
+    const sonnetThinking = models["antigravity-claude-sonnet-4-5-thinking"]
+    const opusThinking = models["antigravity-claude-opus-4-5-thinking"]
+
+    // #then both should have low and max variants
+    for (const model of [sonnetThinking, opusThinking]) {
+      expect(model.variants).toBeTruthy()
+      expect(model.variants.low).toBeTruthy()
+      expect(model.variants.max).toBeTruthy()
+    }
+  })
 })
 
 describe("generateOmoConfig - model fallback system", () => {

src/cli/config-manager.ts

@@ -497,38 +497,61 @@ export async function runBunInstallWithDetails(): Promise<BunInstallResult> {
  *
  * IMPORTANT: Model names MUST use `antigravity-` prefix for stability.
  *
- * The opencode-antigravity-auth plugin supports two naming conventions:
- * - `antigravity-gemini-3-pro-high` (RECOMMENDED, explicit Antigravity quota routing)
- * - `gemini-3-pro-high` (LEGACY, backward compatible but may break in future)
+ * Since opencode-antigravity-auth v1.3.0, models use a variant system:
+ * - `antigravity-gemini-3-pro` with variants: low, high
+ * - `antigravity-gemini-3-flash` with variants: minimal, low, medium, high
  *
- * Legacy names rely on Gemini CLI using `-preview` suffix for disambiguation.
- * If Google removes `-preview`, legacy names may route to wrong quota.
+ * Legacy tier-suffixed names (e.g., `antigravity-gemini-3-pro-high`) still work
+ * but variants are the recommended approach.
  *
- * @see https://github.com/NoeFabris/opencode-antigravity-auth#migration-guide-v127
+ * @see https://github.com/NoeFabris/opencode-antigravity-auth#models
  */
 export const ANTIGRAVITY_PROVIDER_CONFIG = {
   google: {
     name: "Google",
     models: {
-      "antigravity-gemini-3-pro-high": {
-        name: "Gemini 3 Pro High (Antigravity)",
-        thinking: true,
-        attachment: true,
-        limit: { context: 1048576, output: 65535 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-      },
-      "antigravity-gemini-3-pro-low": {
-        name: "Gemini 3 Pro Low (Antigravity)",
-        thinking: true,
-        attachment: true,
+      "antigravity-gemini-3-pro": {
+        name: "Gemini 3 Pro (Antigravity)",
         limit: { context: 1048576, output: 65535 },
         modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingLevel: "low" },
+          high: { thinkingLevel: "high" },
+        },
       },
       "antigravity-gemini-3-flash": {
         name: "Gemini 3 Flash (Antigravity)",
-        attachment: true,
         limit: { context: 1048576, output: 65536 },
         modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          minimal: { thinkingLevel: "minimal" },
+          low: { thinkingLevel: "low" },
+          medium: { thinkingLevel: "medium" },
+          high: { thinkingLevel: "high" },
+        },
+      },
+      "antigravity-claude-sonnet-4-5": {
+        name: "Claude Sonnet 4.5 (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+      },
+      "antigravity-claude-sonnet-4-5-thinking": {
+        name: "Claude Sonnet 4.5 Thinking (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingConfig: { thinkingBudget: 8192 } },
+          max: { thinkingConfig: { thinkingBudget: 32768 } },
+        },
+      },
+      "antigravity-claude-opus-4-5-thinking": {
+        name: "Claude Opus 4.5 Thinking (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingConfig: { thinkingBudget: 8192 } },
+          max: { thinkingConfig: { thinkingBudget: 32768 } },
+        },
       },
     },
   },

src/features/AGENTS.md

@@ -12,12 +12,14 @@ features/
 │   ├── manager.ts              # Launch → poll → complete
 │   ├── concurrency.ts          # Per-provider limits
 │   └── types.ts                # BackgroundTask, LaunchInput
-├── skill-mcp-manager/          # MCP client lifecycle
+├── skill-mcp-manager/          # MCP client lifecycle (520 lines)
 │   ├── manager.ts              # Lazy loading, cleanup
 │   └── types.ts                # SkillMcpConfig
 ├── builtin-skills/             # Playwright, git-master, frontend-ui-ux
 │   └── skills.ts               # 1203 lines
-├── builtin-commands/           # ralph-loop, refactor, init-deep
+├── builtin-commands/           # ralph-loop, refactor, init-deep, start-work, remove-deadcode
+│   ├── commands.ts             # Command registry
+│   └── templates/              # Command templates (4 files)
 ├── claude-code-agent-loader/   # ~/.claude/agents/*.md
 ├── claude-code-command-loader/ # ~/.claude/commands/*.md
 ├── claude-code-mcp-loader/     # .mcp.json
@@ -26,7 +28,8 @@ features/
 ├── opencode-skill-loader/      # Skills from 6 directories
 ├── context-injector/           # AGENTS.md/README.md injection
 ├── boulder-state/              # Todo state persistence
-└── hook-message-injector/      # Message injection
+├── hook-message-injector/      # Message injection
+└── task-toast-manager/         # Background task notifications
 ```
 
 ## LOADER PRIORITY

src/features/builtin-commands/commands.ts

@@ -81,7 +81,7 @@ export function loadBuiltinCommands(
   for (const [name, definition] of Object.entries(BUILTIN_COMMAND_DEFINITIONS)) {
     if (!disabled.has(name as BuiltinCommandName)) {
       const { argumentHint: _argumentHint, ...openCodeCompatible } = definition
-      commands[name] = openCodeCompatible as CommandDefinition
+      commands[name] = { ...openCodeCompatible, name } as CommandDefinition
     }
   }
 

src/features/builtin-commands/templates/ralph-loop.ts

@@ -17,7 +17,7 @@ export const RALPH_LOOP_TEMPLATE = `You are starting a Ralph Loop - a self-refer
 
 ## Exit Conditions
 
-1. **Completion**: Output \`<promise>DONE</promise>\` (or custom promise text) when fully complete
+1. **Completion**: Output your completion promise tag when fully complete
 2. **Max Iterations**: Loop stops automatically at limit
 3. **Cancel**: User runs \`/cancel-ralph\` command
 

src/features/builtin-skills/git-master/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: git-master
-description: "MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'."
+description: "MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'."
 ---
 
 # Git Master Agent

src/features/builtin-skills/skills.ts

@@ -95,7 +95,7 @@ Interpret creatively and make unexpected choices that feel genuinely designed fo
 const gitMasterSkill: BuiltinSkill = {
   name: "git-master",
   description:
-    "MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.",
+    "MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with delegate_task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.",
   template: `# Git Master Agent
 
 You are a Git expert combining three specializations:

src/hooks/AGENTS.md

@@ -10,7 +10,7 @@
 hooks/
 ├── atlas/                      # Main orchestration (773 lines)
 ├── anthropic-context-window-limit-recovery/  # Auto-summarize
-├── todo-continuation-enforcer.ts # Force TODO completion
+├── todo-continuation-enforcer.ts # Force TODO completion (489 lines)
 ├── ralph-loop/                 # Self-referential dev loop
 ├── claude-code-hooks/          # settings.json compat layer - see AGENTS.md
 ├── comment-checker/            # Prevents AI slop
@@ -28,7 +28,15 @@ hooks/
 ├── prometheus-md-only/         # Planner read-only mode
 ├── agent-usage-reminder/       # Specialized agent hints
 ├── auto-update-checker/        # Plugin update check
-└── tool-output-truncator.ts    # Prevents context bloat
+├── tool-output-truncator.ts    # Prevents context bloat
+├── compaction-context-injector/ # Injects context on compaction
+├── delegate-task-retry/        # Retries failed delegations
+├── interactive-bash-session/   # Tmux session management
+├── non-interactive-env/        # Non-TTY environment handling
+├── start-work/                 # Sisyphus work session starter
+├── task-resume-info/           # Resume info for cancelled tasks
+├── question-label-truncator/   # Auto-truncates question labels >30 chars
+└── index.ts                    # Hook aggregation + registration
 ```
 
 ## HOOK EVENTS

src/hooks/atlas/index.test.ts

@@ -141,7 +141,7 @@ describe("atlas hook", () => {
       // #then - standalone verification reminder appended
       expect(output.output).toContain("Task completed successfully")
       expect(output.output).toContain("MANDATORY:")
-      expect(output.output).toContain("delegate_task(resume=")
+      expect(output.output).toContain("delegate_task(session_id=")
       
       cleanupMessageStorage(sessionID)
     })
@@ -180,7 +180,7 @@ describe("atlas hook", () => {
       expect(output.output).toContain("SUBAGENT WORK COMPLETED")
       expect(output.output).toContain("test-plan")
       expect(output.output).toContain("LIE")
-      expect(output.output).toContain("delegate_task(resume=")
+      expect(output.output).toContain("delegate_task(session_id=")
       
       cleanupMessageStorage(sessionID)
     })
@@ -332,7 +332,7 @@ describe("atlas hook", () => {
       cleanupMessageStorage(sessionID)
     })
 
-     test("should include resume and checkbox instructions in reminder", async () => {
+     test("should include session_id and checkbox instructions in reminder", async () => {
        // #given - boulder state, Atlas caller
        const sessionID = "session-resume-test"
        setupMessageStorage(sessionID, "atlas")
@@ -361,8 +361,8 @@ describe("atlas hook", () => {
         output
       )
 
-      // #then - should include resume instructions and verification
-      expect(output.output).toContain("delegate_task(resume=")
+      // #then - should include session_id instructions and verification
+      expect(output.output).toContain("delegate_task(session_id=")
       expect(output.output).toContain("[x]")
       expect(output.output).toContain("MANDATORY:")
       

src/hooks/atlas/index.ts

@@ -179,13 +179,13 @@ If you were NOT given **exactly ONE atomic task**, you MUST:
 `
 
 function buildVerificationReminder(sessionId: string): string {
-  return `${VERIFICATION_REMINDER}
+   return `${VERIFICATION_REMINDER}
 
 ---
 
 **If ANY verification fails, use this immediately:**
 \`\`\`
-delegate_task(resume="${sessionId}", prompt="fix: [describe the specific failure]")
+delegate_task(session_id="${sessionId}", prompt="fix: [describe the specific failure]")
 \`\`\``
 }
 
@@ -711,8 +711,8 @@ export function createAtlasHook(
         return
       }
 
-      const outputStr = output.output && typeof output.output === "string" ? output.output : ""
-      const isBackgroundLaunch = outputStr.includes("Background task launched") || outputStr.includes("Background task resumed")
+       const outputStr = output.output && typeof output.output === "string" ? output.output : ""
+       const isBackgroundLaunch = outputStr.includes("Background task launched") || outputStr.includes("Background task continued")
       
       if (isBackgroundLaunch) {
         return

src/hooks/background-compaction/index.ts

@@ -1,87 +0,0 @@
-import type { BackgroundManager } from "../../features/background-agent"
-
-interface CompactingInput {
-  sessionID: string
-}
-
-interface CompactingOutput {
-  context: string[]
-  prompt?: string
-}
-
-/**
- * Background agent compaction hook - preserves task state during context compaction.
- * 
- * When OpenCode compacts session context to save tokens, this hook injects
- * information about running and recently completed background tasks so the
- * agent doesn't lose awareness of delegated work.
- */
-export function createBackgroundCompactionHook(manager: BackgroundManager) {
-  return {
-    "experimental.session.compacting": async (
-      input: CompactingInput,
-      output: CompactingOutput
-    ): Promise<void> => {
-      const { sessionID } = input
-
-      // Get running tasks for this session
-      const running = manager.getRunningTasks()
-        .filter(t => t.parentSessionID === sessionID)
-        .map(t => ({
-          id: t.id,
-          agent: t.agent,
-          description: t.description,
-          startedAt: t.startedAt,
-        }))
-
-      // Get recently completed tasks (still in memory within 5-min retention)
-      const completed = manager.getCompletedTasks()
-        .filter(t => t.parentSessionID === sessionID)
-        .slice(-10) // Last 10 completed
-        .map(t => ({
-          id: t.id,
-          agent: t.agent,
-          description: t.description,
-          status: t.status,
-        }))
-
-      // Early exit if nothing to preserve
-      if (running.length === 0 && completed.length === 0) return
-
-      const sections: string[] = ["<background-tasks>"]
-
-      // Running tasks section
-      if (running.length > 0) {
-        sections.push("## Running Background Tasks")
-        sections.push("")
-        for (const t of running) {
-          const elapsed = t.startedAt 
-            ? Math.floor((Date.now() - t.startedAt.getTime()) / 1000)
-            : 0
-          sections.push(`- **\`${t.id}\`** (${t.agent}): ${t.description} [${elapsed}s elapsed]`)
-        }
-        sections.push("")
-        sections.push("> **Note:** You WILL be notified when tasks complete.")
-        sections.push("> Do NOT poll - continue productive work.")
-        sections.push("")
-      }
-
-      // Completed tasks section
-      if (completed.length > 0) {
-        sections.push("## Recently Completed Tasks")
-        sections.push("")
-        for (const t of completed) {
-          const statusLabel = t.status === "completed" ? "[DONE]" : t.status === "error" ? "[ERROR]" : "[PENDING]"
-          sections.push(`- ${statusLabel} **\`${t.id}\`**: ${t.description}`)
-        }
-        sections.push("")
-      }
-
-      sections.push("## Retrieval")
-      sections.push('Use `background_output(task_id="<id>")` to retrieve task results.')
-      sections.push("</background-tasks>")
-
-      output.context.push(sections.join("\n"))
-    }
-  }
-}

src/hooks/keyword-detector/constants.ts

@@ -169,10 +169,10 @@ TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
 ## AGENTS / **CATEGORY + SKILLS** UTILIZATION PRINCIPLES (by capability, not by name)
 - **Codebase Exploration**: Spawn exploration agents using BACKGROUND TASKS for file patterns, internal implementations, project structure
 - **Documentation & References**: Use librarian-type agents via BACKGROUND TASKS for API references, examples, external library docs
-- **Planning & Strategy**: NEVER plan yourself - ALWAYS spawn a dedicated planning agent for work breakdown
-  - MUST USE PLAN AGENT. MUST USE PLAN AGENT. MUST USE PLAN AGENT.
-  - ALWAYS ASK PLAN AGENT TO WHAT CATEGORY + SKILLS / AGENTS TO LEVERAGE.
-  - IF IMPLEMENT TASK, MUST ADD TODO NOW: "CONSULT WITH PLAN AGENT WITH CATEGORY + SKILLS"
+- **Planning & Strategy**: NEVER plan yourself - ALWAYS spawn the Plan agent for work breakdown
+  - MUST invoke: \`delegate_task(subagent_type="plan", prompt="<gathered context + user request>")\`
+  - In your prompt to the Plan agent, ASK it to recommend which CATEGORY + SKILLS / AGENTS to leverage for implementation.
+  - IF IMPLEMENT TASK, MUST ADD TODO NOW: "Consult Plan agent via delegate_task(subagent_type='plan') for work breakdown with category + skills recommendations"
 - **High-IQ Reasoning**: Leverage specialized agents for architecture decisions, code review, strategic planning
 - **SPECIAL TASKS COVERED WITH CATEGORY + LOAD_SKILLS**: Delegate to specialized agents with category+skills for design and implementation, as following guide:
   - CATEGORY + SKILL GUIDE
@@ -192,7 +192,7 @@ TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
 ## WORKFLOW
 1. Analyze the request and identify required capabilities
 2. Spawn exploration/librarian agents via delegate_task(background=true) in PARALLEL (10+ if needed)
-3. Always Use Plan agent with gathered context to create detailed work breakdown
+3. Spawn Plan agent: \`delegate_task(subagent_type="plan", prompt="<context + request>")\` to create detailed work breakdown
 4. Execute with continuous verification against original requirements
 
 ## VERIFICATION GUARANTEE (NON-NEGOTIABLE)
@@ -266,9 +266,9 @@ Write these criteria explicitly. Share with user if scope is non-trivial.
 
 THE USER ASKED FOR X. DELIVER EXACTLY X. NOT A SUBSET. NOT A DEMO. NOT A STARTING POINT.
 
-1. EXPLORES + LIBRARIANS
-2. GATHER -> PLAN AGENT SPAWN
-3. WORK BY DELEGATING TO ANOTHER AGENTS
+1. EXPLORES + LIBRARIANS (background)
+2. GATHER -> delegate_task(subagent_type="plan", prompt="<context + request>")
+3. WORK BY DELEGATING TO CATEGORY + SKILLS AGENTS
 
 NOW.
 

src/hooks/ralph-loop/index.test.ts

@@ -459,7 +459,7 @@ describe("ralph-loop", () => {
       })
       hook.startLoop("session-123", "Build something", { completionPromise: "COMPLETE" })
 
-      writeFileSync(transcriptPath, JSON.stringify({ content: "Task done <promise>COMPLETE</promise>" }))
+      writeFileSync(transcriptPath, JSON.stringify({ type: "tool_result", tool_name: "write", tool_output: { output: "Task done <promise>COMPLETE</promise>" } }) + "\n")
 
       // #when - session goes idle (transcriptPath now derived from sessionID via getTranscriptPath)
       await hook.event({
@@ -703,10 +703,105 @@ describe("ralph-loop", () => {
       expect(promptCalls[0].text).toContain("2/50")
     })
 
+    test("should NOT detect completion from user message in transcript (issue #622)", async () => {
+      // #given - transcript contains user message with template text that includes completion promise
+      // This reproduces the bug where the RALPH_LOOP_TEMPLATE instructional text
+      // containing `<promise>DONE</promise>` is recorded as a user message and
+      // falsely triggers completion detection
+      const transcriptPath = join(TEST_DIR, "transcript.jsonl")
+      const templateText = `You are starting a Ralph Loop...
+Output <promise>DONE</promise> when fully complete`
+      const userEntry = JSON.stringify({
+        type: "user",
+        timestamp: new Date().toISOString(),
+        content: templateText,
+      })
+      writeFileSync(transcriptPath, userEntry + "\n")
+
+      const hook = createRalphLoopHook(createMockPluginInput(), {
+        getTranscriptPath: () => transcriptPath,
+      })
+      hook.startLoop("session-123", "Build something", { completionPromise: "DONE" })
+
+      // #when - session goes idle
+      await hook.event({
+        event: {
+          type: "session.idle",
+          properties: { sessionID: "session-123" },
+        },
+      })
+
+      // #then - loop should CONTINUE (user message completion promise is instructional, not actual)
+      expect(promptCalls.length).toBe(1)
+      expect(hook.getState()?.iteration).toBe(2)
+    })
+
+    test("should NOT detect completion from continuation prompt in transcript (issue #622)", async () => {
+      // #given - transcript contains continuation prompt (also a user message) with completion promise
+      const transcriptPath = join(TEST_DIR, "transcript.jsonl")
+      const continuationText = `RALPH LOOP 2/100
+When FULLY complete, output: <promise>DONE</promise>
+Original task: Build something`
+      const userEntry = JSON.stringify({
+        type: "user",
+        timestamp: new Date().toISOString(),
+        content: continuationText,
+      })
+      writeFileSync(transcriptPath, userEntry + "\n")
+
+      const hook = createRalphLoopHook(createMockPluginInput(), {
+        getTranscriptPath: () => transcriptPath,
+      })
+      hook.startLoop("session-123", "Build something", { completionPromise: "DONE" })
+
+      // #when - session goes idle
+      await hook.event({
+        event: {
+          type: "session.idle",
+          properties: { sessionID: "session-123" },
+        },
+      })
+
+      // #then - loop should CONTINUE (continuation prompt text is not actual completion)
+      expect(promptCalls.length).toBe(1)
+      expect(hook.getState()?.iteration).toBe(2)
+    })
+
+    test("should detect completion from tool_result entry in transcript", async () => {
+      // #given - transcript contains a tool_result with completion promise
+      const transcriptPath = join(TEST_DIR, "transcript.jsonl")
+      const toolResultEntry = JSON.stringify({
+        type: "tool_result",
+        timestamp: new Date().toISOString(),
+        tool_name: "write",
+        tool_input: {},
+        tool_output: { output: "Task complete! <promise>DONE</promise>" },
+      })
+      writeFileSync(transcriptPath, toolResultEntry + "\n")
+
+      const hook = createRalphLoopHook(createMockPluginInput(), {
+        getTranscriptPath: () => transcriptPath,
+      })
+      hook.startLoop("session-123", "Build something", { completionPromise: "DONE" })
+
+      // #when - session goes idle
+      await hook.event({
+        event: {
+          type: "session.idle",
+          properties: { sessionID: "session-123" },
+        },
+      })
+
+      // #then - loop should complete (tool_result contains actual completion output)
+      expect(promptCalls.length).toBe(0)
+      expect(toastCalls.some((t) => t.title === "Ralph Loop Complete!")).toBe(true)
+      expect(hook.getState()).toBeNull()
+    })
+
     test("should check transcript BEFORE API to optimize performance", async () => {
       // #given - transcript has completion promise
       const transcriptPath = join(TEST_DIR, "transcript.jsonl")
-      writeFileSync(transcriptPath, JSON.stringify({ content: "<promise>DONE</promise>" }))
+      writeFileSync(transcriptPath, JSON.stringify({ type: "tool_result", tool_name: "write", tool_output: { output: "<promise>DONE</promise>" } }) + "\n")
       mockSessionMessages = [
         { info: { role: "assistant" }, parts: [{ type: "text", text: "No promise here" }] },
       ]
@@ -736,7 +831,7 @@ describe("ralph-loop", () => {
       const hook = createRalphLoopHook(createMockPluginInput(), {
         getTranscriptPath: () => transcriptPath,
       })
-      writeFileSync(transcriptPath, JSON.stringify({ content: "<promise>DONE</promise>" }))
+      writeFileSync(transcriptPath, JSON.stringify({ type: "tool_result", tool_name: "write", tool_output: { output: "<promise>DONE</promise>" } }) + "\n")
       hook.startLoop("test-id", "Build API", { ultrawork: true })
 
       // #when - idle event triggered
@@ -754,7 +849,7 @@ describe("ralph-loop", () => {
       const hook = createRalphLoopHook(createMockPluginInput(), {
         getTranscriptPath: () => transcriptPath,
       })
-      writeFileSync(transcriptPath, JSON.stringify({ content: "<promise>DONE</promise>" }))
+      writeFileSync(transcriptPath, JSON.stringify({ type: "tool_result", tool_name: "write", tool_output: { output: "<promise>DONE</promise>" } }) + "\n")
       hook.startLoop("test-id", "Build API")
 
       // #when - idle event triggered

src/hooks/ralph-loop/index.ts

@@ -100,7 +100,18 @@ export function createRalphLoopHook(
 
       const content = readFileSync(transcriptPath, "utf-8")
       const pattern = new RegExp(`<promise>\\s*${escapeRegex(promise)}\\s*</promise>`, "is")
-      return pattern.test(content)
+      const lines = content.split("\n").filter(l => l.trim())
+
+      for (const line of lines) {
+        try {
+          const entry = JSON.parse(line)
+          if (entry.type === "user") continue
+          if (pattern.test(line)) return true
+        } catch {
+          continue
+        }
+      }
+      return false
     } catch {
       return false
     }

src/hooks/task-resume-info/index.ts

@@ -16,21 +16,21 @@ function extractSessionId(output: string): string | null {
 }
 
 export function createTaskResumeInfoHook() {
-  const toolExecuteAfter = async (
-    input: { tool: string; sessionID: string; callID: string },
-    output: { title: string; output: string; metadata: unknown }
-  ) => {
-    if (!TARGET_TOOLS.includes(input.tool)) return
-    if (output.output.startsWith("Error:") || output.output.startsWith("Failed")) return
-    if (output.output.includes("\nto resume:")) return
+   const toolExecuteAfter = async (
+     input: { tool: string; sessionID: string; callID: string },
+     output: { title: string; output: string; metadata: unknown }
+   ) => {
+     if (!TARGET_TOOLS.includes(input.tool)) return
+     if (output.output.startsWith("Error:") || output.output.startsWith("Failed")) return
+     if (output.output.includes("\nto continue:")) return
 
-    const sessionId = extractSessionId(output.output)
-    if (!sessionId) return
+     const sessionId = extractSessionId(output.output)
+     if (!sessionId) return
 
-    output.output = output.output.trimEnd() + `\n\nto resume: delegate_task(resume="${sessionId}", prompt="...")`
-  }
+     output.output = output.output.trimEnd() + `\n\nto continue: delegate_task(session_id="${sessionId}", prompt="...")`
+   }
 
-  return {
-    "tool.execute.after": toolExecuteAfter,
-  }
+   return {
+     "tool.execute.after": toolExecuteAfter,
+   }
 }

src/shared/AGENTS.md

@@ -2,7 +2,7 @@
 
 ## OVERVIEW
 
-50 cross-cutting utilities: path resolution, token truncation, config parsing, model resolution.
+34 cross-cutting utilities: path resolution, token truncation, config parsing, model resolution, agent display names.
 
 ## STRUCTURE
 
@@ -19,12 +19,27 @@ shared/
 ├── migration.ts           # Legacy config migration
 ├── opencode-version.ts    # Version comparison
 ├── external-plugin-detector.ts # OAuth spoofing detection
-├── env-expander.ts        # ${VAR} expansion
 ├── model-requirements.ts  # Agent/Category requirements
 ├── model-availability.ts  # Models fetch + fuzzy match
 ├── model-resolver.ts      # 3-step resolution
+├── model-sanitizer.ts     # Model ID normalization
 ├── shell-env.ts           # Cross-platform shell
-├── prompt-parts-helper.ts # Prompt manipulation
+├── agent-display-names.ts # Agent display name mapping
+├── agent-tool-restrictions.ts # Tool restriction helpers
+├── agent-variant.ts       # Agent variant detection
+├── command-executor.ts    # Subprocess execution
+├── config-errors.ts       # Config error types
+├── deep-merge.ts          # Deep object merge
+├── file-reference-resolver.ts # File path resolution
+├── file-utils.ts          # File utilities
+├── hook-disabled.ts       # Hook enable/disable check
+├── pattern-matcher.ts     # Glob pattern matching
+├── session-cursor.ts      # Session cursor tracking
+├── snake-case.ts          # String case conversion
+├── system-directive.ts    # System prompt helpers
+├── tool-name.ts           # Tool name constants
+├── zip-extractor.ts       # ZIP file extraction
+├── index.ts               # Barrel export
 └── *.test.ts              # Colocated tests
 ```
 
@@ -40,6 +55,7 @@ shared/
 | Resolve paths | `getOpenCodeConfigDir()` |
 | Compare versions | `isOpenCodeVersionAtLeast("1.1.0")` |
 | Resolve model | `resolveModelWithFallback()` |
+| Agent display name | `getAgentDisplayName(agentName)` |
 
 ## PATTERNS
 

src/shared/config-path.ts

@@ -1,43 +0,0 @@
-import * as path from "path"
-import * as os from "os"
-import * as fs from "fs"
-
-/**
- * Returns the user-level config directory based on the OS.
- * @deprecated Use getOpenCodeConfigDir() from opencode-config-dir.ts instead.
- */
-export function getUserConfigDir(): string {
-  if (process.platform === "win32") {
-    const crossPlatformDir = path.join(os.homedir(), ".config")
-    const crossPlatformConfigPath = path.join(crossPlatformDir, "opencode", "oh-my-opencode.json")
-
-    const appdataDir = process.env.APPDATA || path.join(os.homedir(), "AppData", "Roaming")
-    const appdataConfigPath = path.join(appdataDir, "opencode", "oh-my-opencode.json")
-
-    if (fs.existsSync(crossPlatformConfigPath)) {
-      return crossPlatformDir
-    }
-
-    if (fs.existsSync(appdataConfigPath)) {
-      return appdataDir
-    }
-
-    return crossPlatformDir
-  }
-
-  return process.env.XDG_CONFIG_HOME || path.join(os.homedir(), ".config")
-}
-
-/**
- * Returns the full path to the user-level oh-my-opencode config file.
- */
-export function getUserConfigPath(): string {
-  return path.join(getUserConfigDir(), "opencode", "oh-my-opencode.json")
-}
-
-/**
- * Returns the full path to the project-level oh-my-opencode config file.
- */
-export function getProjectConfigPath(directory: string): string {
-  return path.join(directory, ".opencode", "oh-my-opencode.json")
-}

src/shared/index.ts

@@ -10,7 +10,6 @@ export * from "./hook-disabled"
 export * from "./deep-merge"
 export * from "./file-utils"
 export * from "./dynamic-truncator"
-export * from "./config-path"
 export * from "./data-path"
 export * from "./config-errors"
 export * from "./claude-config-dir"

src/shared/model-resolver.test.ts

@@ -236,9 +236,9 @@ describe("resolveModelWithFallback", () => {
       // #given
       const input: ExtendedModelResolutionInput = {
         fallbackChain: [
-          { providers: ["anthropic", "opencode", "github-copilot"], model: "gpt-5-nano" },
+          { providers: ["anthropic", "opencode"], model: "gpt-5-nano" },
         ],
-        availableModels: new Set(["opencode/gpt-5-nano", "github-copilot/gpt-5-nano-preview"]),
+        availableModels: new Set(["opencode/gpt-5-nano"]),
         systemDefaultModel: "google/gemini-3-pro",
       }
 

src/tools/AGENTS.md

@@ -25,7 +25,7 @@ tools/
 ├── skill-mcp/        # Skill MCP operations
 ├── slashcommand/     # Slash command dispatch
 ├── call-omo-agent/   # Direct agent invocation
-└── background-task/  # background_output, background_cancel
+└── background-task/  # background_output, background_cancel (513 lines)
 ```
 
 ## TOOL CATEGORIES
@@ -48,7 +48,7 @@ tools/
 
 ## LSP SPECIFICS
 
-- **Client**: `client.ts` manages stdio, JSON-RPC
+- **Client**: `client.ts` manages stdio, JSON-RPC (596 lines)
 - **Singleton**: `LSPServerManager` with ref counting
 - **Capabilities**: definition, references, symbols, diagnostics, rename
 

src/tools/background-task/tools.ts

@@ -442,18 +442,18 @@ export function createBackgroundCancel(manager: BackgroundManager, client: Openc
             .map(t => `| \`${t.id}\` | ${t.description} | ${t.status} | ${t.sessionID ? `\`${t.sessionID}\`` : "(not started)"} |`)
             .join("\n")
 
-          const resumableTasks = cancelledInfo.filter(t => t.sessionID)
-          const resumeSection = resumableTasks.length > 0
-            ? `\n## Resume Instructions
+           const resumableTasks = cancelledInfo.filter(t => t.sessionID)
+           const resumeSection = resumableTasks.length > 0
+             ? `\n## Continue Instructions
 
-To resume a cancelled task, use:
+To continue a cancelled task, use:
 \`\`\`
-delegate_task(resume="<session_id>", prompt="Continue: <your follow-up>")
+delegate_task(session_id="<session_id>", prompt="Continue: <your follow-up>")
 \`\`\`
 
-Resumable sessions:
+Continuable sessions:
 ${resumableTasks.map(t => `- \`${t.sessionID}\` (${t.description})`).join("\n")}`
-            : ""
+             : ""
 
           return `Cancelled ${cancellableTasks.length} background task(s):
 

src/tools/call-omo-agent/constants.ts

@@ -4,4 +4,4 @@ export const CALL_OMO_AGENT_DESCRIPTION = `Spawn explore/librarian agent. run_in
 
 Available: {agents}
 
-Pass \`resume=session_id\` to continue previous agent with full context. Prompts MUST be in English. Use \`background_output\` for async results.`
+Pass \`session_id=<id>\` to continue previous agent with full context. Prompts MUST be in English. Use \`background_output\` for async results.`

src/tools/delegate-task/tools.test.ts

@@ -594,16 +594,16 @@ describe("sisyphus-task", () => {
     }, { timeout: 20000 })
   })
 
-  describe("resume with background parameter", () => {
-  test("resume with background=false should wait for result and return content", async () => {
+  describe("session_id with background parameter", () => {
+  test("session_id with background=false should wait for result and return content", async () => {
     // Note: This test needs extended timeout because the implementation has MIN_STABILITY_TIME_MS = 5000
     // #given
     const { createDelegateTask } = require("./tools")
     
     const mockTask = {
       id: "task-123",
-      sessionID: "ses_resume_test",
-      description: "Resumed task",
+      sessionID: "ses_continue_test",
+      description: "Continued task",
       agent: "explore",
       status: "running",
     }
@@ -620,7 +620,7 @@ describe("sisyphus-task", () => {
           data: [
             {
               info: { role: "assistant", time: { created: Date.now() } },
-              parts: [{ type: "text", text: "This is the resumed task result" }],
+              parts: [{ type: "text", text: "This is the continued task result" }],
             },
           ],
         }),
@@ -646,28 +646,28 @@ describe("sisyphus-task", () => {
     // #when
     const result = await tool.execute(
       {
-        description: "Resume test",
+        description: "Continue test",
         prompt: "Continue the task",
-        resume: "ses_resume_test",
+        session_id: "ses_continue_test",
         run_in_background: false,
         load_skills: ["git-master"],
       },
       toolContext
     )
     
-    // #then - should contain actual result, not just "Background task resumed"
-    expect(result).toContain("This is the resumed task result")
-    expect(result).not.toContain("Background task resumed")
+    // #then - should contain actual result, not just "Background task continued"
+    expect(result).toContain("This is the continued task result")
+    expect(result).not.toContain("Background task continued")
   }, { timeout: 10000 })
 
-  test("resume with background=true should return immediately without waiting", async () => {
+  test("session_id with background=true should return immediately without waiting", async () => {
     // #given
     const { createDelegateTask } = require("./tools")
     
     const mockTask = {
       id: "task-456",
-      sessionID: "ses_bg_resume",
-      description: "Background resumed task",
+      sessionID: "ses_bg_continue",
+      description: "Background continued task",
       agent: "explore",
       status: "running",
     }
@@ -701,9 +701,9 @@ describe("sisyphus-task", () => {
     // #when
     const result = await tool.execute(
       {
-        description: "Resume bg test",
+        description: "Continue bg test",
         prompt: "Continue in background",
-        resume: "ses_bg_resume",
+        session_id: "ses_bg_continue",
         run_in_background: true,
         load_skills: ["git-master"],
       },
@@ -711,7 +711,7 @@ describe("sisyphus-task", () => {
     )
     
     // #then - should return background message
-    expect(result).toContain("Background task resumed")
+    expect(result).toContain("Background task continued")
     expect(result).toContain("task-456")
   })
 })

src/tools/delegate-task/tools.ts

@@ -86,8 +86,8 @@ function formatDetailedError(error: unknown, ctx: ErrorContext): string {
     lines.push(`- subagent_type: ${ctx.args.subagent_type ?? "(none)"}`)
     lines.push(`- run_in_background: ${ctx.args.run_in_background}`)
     lines.push(`- load_skills: [${ctx.args.load_skills?.join(", ") ?? ""}]`)
-    if (ctx.args.resume) {
-      lines.push(`- resume: ${ctx.args.resume}`)
+    if (ctx.args.session_id) {
+      lines.push(`- session_id: ${ctx.args.session_id}`)
     }
   }
 
@@ -194,7 +194,7 @@ export function createDelegateTask(options: DelegateTaskToolOptions): ToolDefini
 
   const description = `Spawn agent task with category-based or direct agent selection.
 
-MUTUALLY EXCLUSIVE: Provide EITHER category OR subagent_type, not both (unless resuming).
+MUTUALLY EXCLUSIVE: Provide EITHER category OR subagent_type, not both (unless continuing a session).
 
 - load_skills: ALWAYS REQUIRED. Pass at least one skill name (e.g., ["playwright"], ["git-master", "frontend-ui-ux"]).
 - category: Use predefined category → Spawns Sisyphus-Junior with category config
@@ -202,12 +202,13 @@ MUTUALLY EXCLUSIVE: Provide EITHER category OR subagent_type, not both (unless r
 ${categoryList}
 - subagent_type: Use specific agent directly (e.g., "oracle", "explore")
 - run_in_background: true=async (returns task_id), false=sync (waits for result). Default: false. Use background=true ONLY for parallel exploration with 5+ independent queries.
-- resume: Session ID to resume (from previous task output). Continues agent with FULL CONTEXT PRESERVED - saves tokens, maintains continuity.
+- session_id: Existing Task session to continue (from previous task output). Continues agent with FULL CONTEXT PRESERVED - saves tokens, maintains continuity.
+- command: The command that triggered this task (optional, for slash command tracking).
 
-**WHEN TO USE resume:**
-- Task failed/incomplete → resume with "fix: [specific issue]"
-- Need follow-up on previous result → resume with additional question
-- Multi-turn conversation with same agent → always resume instead of new task
+**WHEN TO USE session_id:**
+- Task failed/incomplete → session_id with "fix: [specific issue]"
+- Need follow-up on previous result → session_id with additional question
+- Multi-turn conversation with same agent → always session_id instead of new task
 
 Prompts MUST be in English.`
 
@@ -220,7 +221,8 @@ Prompts MUST be in English.`
       run_in_background: tool.schema.boolean().describe("true=async (returns task_id), false=sync (waits). Default: false"),
       category: tool.schema.string().optional().describe(`Category (e.g., ${categoryExamples}). Mutually exclusive with subagent_type.`),
       subagent_type: tool.schema.string().optional().describe("Agent name (e.g., 'oracle', 'explore'). Mutually exclusive with category."),
-      resume: tool.schema.string().optional().describe("Session ID to resume"),
+      session_id: tool.schema.string().optional().describe("Existing Task session to continue"),
+      command: tool.schema.string().optional().describe("The command that triggered this task"),
     },
     async execute(args: DelegateTaskArgs, toolContext) {
       const ctx = toolContext as ToolContextWithMetadata
@@ -265,11 +267,11 @@ Prompts MUST be in English.`
         ? { providerID: prevMessage.model.providerID, modelID: prevMessage.model.modelID }
         : undefined
 
-      if (args.resume) {
+      if (args.session_id) {
         if (runInBackground) {
           try {
             const task = await manager.resume({
-              sessionId: args.resume,
+              sessionId: args.session_id,
               prompt: args.prompt,
               parentSessionID: ctx.sessionID,
               parentMessageID: ctx.messageID,
@@ -278,7 +280,7 @@ Prompts MUST be in English.`
             })
 
             ctx.metadata?.({
-              title: `Resume: ${task.description}`,
+              title: `Continue: ${task.description}`,
               metadata: {
                 prompt: args.prompt,
                 agent: task.agent,
@@ -286,10 +288,11 @@ Prompts MUST be in English.`
                 description: args.description,
                 run_in_background: args.run_in_background,
                 sessionId: task.sessionID,
+                command: args.command,
               },
             })
 
-            return `Background task resumed.
+            return `Background task continued.
 
 Task ID: ${task.id}
 Session ID: ${task.sessionID}
@@ -301,35 +304,36 @@ Agent continues with full previous context preserved.
 Use \`background_output\` with task_id="${task.id}" to check progress.`
           } catch (error) {
             return formatDetailedError(error, {
-              operation: "Resume background task",
+              operation: "Continue background task",
               args,
-              sessionID: args.resume,
+              sessionID: args.session_id,
             })
           }
         }
 
         const toastManager = getTaskToastManager()
-        const taskId = `resume_sync_${args.resume.slice(0, 8)}`
+        const taskId = `resume_sync_${args.session_id.slice(0, 8)}`
         const startTime = new Date()
 
         if (toastManager) {
           toastManager.addTask({
             id: taskId,
             description: args.description,
-            agent: "resume",
+            agent: "continue",
             isBackground: false,
           })
         }
 
         ctx.metadata?.({
-          title: `Resume: ${args.description}`,
+          title: `Continue: ${args.description}`,
           metadata: {
             prompt: args.prompt,
             load_skills: args.load_skills,
             description: args.description,
             run_in_background: args.run_in_background,
-            sessionId: args.resume,
+            sessionId: args.session_id,
             sync: true,
+            command: args.command,
           },
         })
 
@@ -338,7 +342,7 @@ Use \`background_output\` with task_id="${task.id}" to check progress.`
           let resumeModel: { providerID: string; modelID: string } | undefined
 
           try {
-            const messagesResp = await client.session.messages({ path: { id: args.resume } })
+            const messagesResp = await client.session.messages({ path: { id: args.session_id } })
             const messages = (messagesResp.data ?? []) as Array<{
               info?: { agent?: string; model?: { providerID: string; modelID: string }; modelID?: string; providerID?: string }
             }>
@@ -351,7 +355,7 @@ Use \`background_output\` with task_id="${task.id}" to check progress.`
               }
             }
           } catch {
-            const resumeMessageDir = getMessageDir(args.resume)
+            const resumeMessageDir = getMessageDir(args.session_id)
             const resumeMessage = resumeMessageDir ? findNearestMessageWithFields(resumeMessageDir) : null
             resumeAgent = resumeMessage?.agent
             resumeModel = resumeMessage?.model?.providerID && resumeMessage?.model?.modelID
@@ -360,7 +364,7 @@ Use \`background_output\` with task_id="${task.id}" to check progress.`
           }
 
           await client.session.prompt({
-            path: { id: args.resume },
+            path: { id: args.session_id },
             body: {
               ...(resumeAgent !== undefined ? { agent: resumeAgent } : {}),
               ...(resumeModel !== undefined ? { model: resumeModel } : {}),
@@ -378,7 +382,7 @@ Use \`background_output\` with task_id="${task.id}" to check progress.`
             toastManager.removeTask(taskId)
           }
           const errorMessage = promptError instanceof Error ? promptError.message : String(promptError)
-          return `Failed to send resume prompt: ${errorMessage}\n\nSession ID: ${args.resume}`
+          return `Failed to send continuation prompt: ${errorMessage}\n\nSession ID: ${args.session_id}`
         }
 
         // Wait for message stability after prompt completes
@@ -395,7 +399,7 @@ Use \`background_output\` with task_id="${task.id}" to check progress.`
           const elapsed = Date.now() - pollStart
           if (elapsed < MIN_STABILITY_TIME_MS) continue
 
-          const messagesCheck = await client.session.messages({ path: { id: args.resume } })
+          const messagesCheck = await client.session.messages({ path: { id: args.session_id } })
           const msgs = ((messagesCheck as { data?: unknown }).data ?? messagesCheck) as Array<unknown>
           const currentMsgCount = msgs.length
 
@@ -409,14 +413,14 @@ Use \`background_output\` with task_id="${task.id}" to check progress.`
         }
 
         const messagesResult = await client.session.messages({
-          path: { id: args.resume },
+          path: { id: args.session_id },
         })
 
         if (messagesResult.error) {
           if (toastManager) {
             toastManager.removeTask(taskId)
           }
-          return `Error fetching result: ${messagesResult.error}\n\nSession ID: ${args.resume}`
+          return `Error fetching result: ${messagesResult.error}\n\nSession ID: ${args.session_id}`
         }
 
         const messages = ((messagesResult as { data?: unknown }).data ?? messagesResult) as Array<{
@@ -434,7 +438,7 @@ Use \`background_output\` with task_id="${task.id}" to check progress.`
         }
 
         if (!lastMessage) {
-          return `No assistant response found.\n\nSession ID: ${args.resume}`
+          return `No assistant response found.\n\nSession ID: ${args.session_id}`
         }
 
         // Extract text from both "text" and "reasoning" parts (thinking models use "reasoning")
@@ -443,16 +447,16 @@ Use \`background_output\` with task_id="${task.id}" to check progress.`
 
         const duration = formatDuration(startTime)
 
-        return `Task resumed and completed in ${duration}.
+        return `Task continued and completed in ${duration}.
 
-Session ID: ${args.resume}
+Session ID: ${args.session_id}
 
 ---
 
 ${textContent || "(No text output)"}
 
 ---
-To resume this session: resume="${args.resume}"`
+To continue this session: session_id="${args.session_id}"`
       }
 
       if (args.category && args.subagent_type) {
@@ -618,6 +622,7 @@ To resume this session: resume="${args.resume}"`
                 description: args.description,
                 run_in_background: args.run_in_background,
                 sessionId: sessionID,
+                command: args.command,
               },
             })
 
@@ -705,7 +710,7 @@ RESULT:
 ${textContent || "(No text output)"}
 
 ---
-To resume this session: resume="${sessionID}"`
+To continue this session: session_id="${sessionID}"`
           } catch (error) {
             return formatDetailedError(error, {
               operation: "Launch monitored background task",
@@ -788,6 +793,7 @@ Sisyphus-Junior is spawned automatically when you specify a category. Pick the a
               description: args.description,
               run_in_background: args.run_in_background,
               sessionId: task.sessionID,
+              command: args.command,
             },
           })
 
@@ -800,7 +806,7 @@ Agent: ${task.agent}${args.category ? ` (category: ${args.category})` : ""}
 Status: ${task.status}
 
 System notifies on completion. Use \`background_output\` with task_id="${task.id}" to check.
-To resume this session: resume="${task.sessionID}"`
+To continue this session: session_id="${task.sessionID}"`
         } catch (error) {
           return formatDetailedError(error, {
             operation: "Launch background task",
@@ -864,6 +870,7 @@ To resume this session: resume="${task.sessionID}"`
             run_in_background: args.run_in_background,
             sessionId: sessionID,
             sync: true,
+            command: args.command,
           },
         })
 
@@ -1018,7 +1025,7 @@ Session ID: ${sessionID}
 ${textContent || "(No text output)"}
 
 ---
-To resume this session: resume="${sessionID}"`
+To continue this session: session_id="${sessionID}"`
       } catch (error) {
         if (toastManager && taskId !== undefined) {
           toastManager.removeTask(taskId)

src/tools/delegate-task/types.ts

@@ -4,6 +4,7 @@ export interface DelegateTaskArgs {
   category?: string
   subagent_type?: string
   run_in_background: boolean
-  resume?: string
+  session_id?: string
+  command?: string
   load_skills: string[]
 }

src/tools/index.ts

@@ -30,7 +30,6 @@ export { sessionExists } from "./session-manager/storage"
 
 export { interactive_bash, startBackgroundCheck as startTmuxCheck } from "./interactive-bash"
 export { createSkillTool } from "./skill"
-export { getTmuxPath } from "./interactive-bash/utils"
 export { createSkillMcpTool } from "./skill-mcp"
 
 import {
@@ -45,7 +44,7 @@ type OpencodeClient = PluginInput["client"]
 
 export { createCallOmoAgent } from "./call-omo-agent"
 export { createLookAt } from "./look-at"
-export { createDelegateTask, type DelegateTaskToolOptions, DEFAULT_CATEGORIES, CATEGORY_PROMPT_APPENDS } from "./delegate-task"
+export { createDelegateTask } from "./delegate-task"
 
 export function createBackgroundTools(manager: BackgroundManager, client: OpencodeClient): Record<string, ToolDefinition> {
   return {