@charzhu/openjaw-agent 0.2.9 → 0.3.1

package/README.md

@@ -195,6 +195,8 @@ The agent reasons about your request, picks the right tools, executes them, and
 | `/schedule "prompt" every 15m` | Schedule recurring tasks |
 | `/schedule list` | Show active scheduled tasks |
 | `/schedule stop <id>` | Cancel a scheduled task |
+| `/workflow <goal>` | Start an advisory dynamic workflow with read-only workers |
+| `/workflow status [id]` | Open navigable worker status and detail view |
 | `/tools` | List all available tools |
 | `/mcp` | Manage MCP server connections |
 | `/memory` | Search persistent memory |
@@ -350,6 +352,14 @@ Supports **stdio**, **SSE**, and **Streamable HTTP** transports. Tools from exte
 
 Use `/mcp` to interactively manage connections — toggle servers, view tools, reconnect.
 
+## Dynamic Workflows
+
+Use `/workflow <goal>` for complex advisory work that benefits from parallel read-only workers. OpenJaw asks the active model to return a JSON workflow graph, dynamically plans worker count from the goal, schedules workers through an adaptive queue, and shows progress in the `/workflow status [id]` overlay. Use arrow keys or `j/k` to select workers, `Enter`/`→` for details, `Esc`/`←` to return, `s` to sort, `f` to filter, and `q` to close.
+
+Workflows include a final synthesizer worker. When the workflow completes, the synthesizer's answer is posted back into the transcript and is also visible through `/workflow show [id]` and the worker details view.
+
+Workflow workers are intentionally non-mutating in this version: they can inspect files and search, but cannot edit files, run shell/code execution, send messages, or update memory. Results are persisted under `~/.openjaw-agent/workflows/` and replayable through the workflow status and spawn-tree archive paths.
+
 ## Architecture
 
 ```

package/config.yaml

@@ -44,6 +44,21 @@ llm:
   # Currently defaults to opencode's client ID because it exposes the full Copilot model list.
   copilot_oauth_client_id: Iv1.b507a08c87ecfe98
 
+features:
+  # Suggest creating a reusable skill after complex multi-step tasks.
+  skill_auto_suggest: true
+
+  # Advisory dynamic workflows started with /workflow.
+  # Workers are read-only: they can inspect/search/verify but cannot edit files,
+  # run shell/code, send messages, or update memory.
+  dynamic_workflows:
+    enabled: true
+    planner_mode: adaptive
+    hard_max_workers: 1024
+    hard_max_concurrent_workers: 128
+    worker_timeout_ms: 180000
+    persist_history: true
+
 # ─── Example: OpenAI direct (normally use: /connect openai <api-key>) ───
 # llm:
 #   provider: openai