feat: Implement context detection and onboarding tools for DevClaw

- Add context-guard.ts to detect interaction context (via-agent, direct, group) and generate guardrails. - Introduce onboarding.ts for conversational onboarding context templates and workspace file checks. - Enhance setup.ts to support new agent creation with channel binding and migration of existing bindings. - Create analyze-channel-bindings.ts to analyze channel availability and detect binding conflicts. - Implement context-test.ts for debugging context detection. - Develop devclaw_onboard.ts for explicit onboarding tool that guides users through setup. - Update devclaw_setup.ts to include channel binding and migration support in setup process. - Modify project-register.ts to enforce project registration from group context and auto-populate group ID. - Enhance queue-status.ts to provide context-aware status checks and recommendations. - Update task tools (task-complete, task-create, task-pickup) to clarify group ID usage for Telegram/WhatsApp.
2026-02-09 18:34:45 +08:00
parent 32eb079521
commit a9a3fc3f1f
18 changed files with 1532 additions and 44 deletions
--- a/lib/onboarding.ts
+++ b/lib/onboarding.ts
@@ -0,0 +1,122 @@
+/**
+ * onboarding.ts — Conversational onboarding context templates.
+ *
+ * Provides context templates for the devclaw_onboard tool.
+ */
+import fs from "node:fs/promises";
+import path from "node:path";
+import { ALL_TIERS, DEFAULT_MODELS, type Tier } from "./tiers.js";
+
+// ---------------------------------------------------------------------------
+// Detection
+// ---------------------------------------------------------------------------
+
+export function isPluginConfigured(
+  pluginConfig?: Record<string, unknown>,
+): boolean {
+  const models = (pluginConfig as { models?: Record<string, string> })?.models;
+  return !!models && Object.keys(models).length > 0;
+}
+
+export async function hasWorkspaceFiles(
+  workspaceDir?: string,
+): Promise<boolean> {
+  if (!workspaceDir) return false;
+  try {
+    const content = await fs.readFile(
+      path.join(workspaceDir, "AGENTS.md"),
+      "utf-8",
+    );
+    return content.includes("DevClaw") && content.includes("task_pickup");
+  } catch {
+    return false;
+  }
+}
+
+// ---------------------------------------------------------------------------
+// Context templates
+// ---------------------------------------------------------------------------
+
+function buildModelTable(pluginConfig?: Record<string, unknown>): string {
+  const models =
+    (pluginConfig as { models?: Record<string, string> })?.models ?? {};
+  return ALL_TIERS.map(
+    (t) =>
+      `  - **${t}**: ${models[t] || DEFAULT_MODELS[t as Tier]} (default: ${DEFAULT_MODELS[t as Tier]})`,
+  ).join("\n");
+}
+
+export function buildReconfigContext(
+  pluginConfig?: Record<string, unknown>,
+): string {
+  const modelTable = buildModelTable(pluginConfig);
+  return `# DevClaw Reconfiguration
+
+The user wants to reconfigure DevClaw. Current model configuration:
+
+${modelTable}
+
+## What can be changed
+1. **Model tiers** — call \`devclaw_setup\` with a \`models\` object containing only the tiers to change
+2. **Workspace files** — \`devclaw_setup\` re-writes AGENTS.md, HEARTBEAT.md (backs up existing files)
+3. **Register new projects** — use \`project_register\`
+
+Ask what they want to change, then call the appropriate tool.
+\`devclaw_setup\` is safe to re-run — it backs up existing files before overwriting.
+`;
+}
+
+export function buildOnboardToolContext(): string {
+  return `# DevClaw Onboarding
+
+## What is DevClaw?
+DevClaw turns each Telegram group into an autonomous development team:
+- An **orchestrator** that manages backlogs and delegates work
+- **DEV workers** (junior/medior/senior tiers) that write code in isolated sessions
+- **QA workers** that review code and run tests
+- Atomic tools for label transitions, session dispatch, state management, and audit logging
+
+## Setup Steps
+
+**Step 1: Agent Selection**
+Ask: "Do you want to configure DevClaw for the current agent, or create a new dedicated agent?"
+- Current agent → no \`newAgentName\` needed
+- New agent → ask for:
+  1. Agent name
+  2. **Channel binding**: "Which channel should this agent listen to? (telegram/whatsapp/none)"
+     - If telegram/whatsapp selected:
+       a) Call \`analyze_channel_bindings\` to check for conflicts
+       b) If channel not configured/enabled → warn and recommend skipping binding for now
+       c) If channel-wide binding exists on another agent → ask: "Migrate binding from {agentName}?"
+       d) Collect migration decision
+     - If none selected, user can add bindings manually later via openclaw.json
+
+**Step 2: Model Configuration**
+Show the default tier-to-model mapping and ask if they want to customize:
+
+| Tier | Default Model | Purpose |
+|------|---------------|---------|
+| junior | anthropic/claude-haiku-4-5 | Typos, single-file fixes |
+| medior | anthropic/claude-sonnet-4-5 | Features, bug fixes |
+| senior | anthropic/claude-opus-4-5 | Architecture, refactoring |
+| qa | anthropic/claude-sonnet-4-5 | Code review, testing |
+
+If the defaults are fine, proceed. If customizing, ask which tiers to change.
+
+**Step 3: Run Setup**
+Call \`devclaw_setup\` with the collected answers:
+- Current agent: \`devclaw_setup({})\` or \`devclaw_setup({ models: { ... } })\`
+- New agent: \`devclaw_setup({ newAgentName: "<name>", channelBinding: "telegram"|"whatsapp"|null, migrateFrom: "<agentId>"|null, models: { ... } })\`
+  - \`migrateFrom\`: Include if user wants to migrate an existing channel-wide binding
+
+**Step 4: Optional Project Registration**
+After setup, ask: "Would you like to register a project now?"
+If yes, collect: project name, repo path, Telegram group ID, group name, base branch.
+Then call \`project_register\`.
+
+## Guidelines
+- Be conversational and friendly. Ask one question at a time.
+- Show defaults so the user can accept them quickly.
+- After setup, summarize what was configured (including channel binding if applicable).
+`;
+}