[pull] main from CodebuffAI:main

AGENTS.md

@@ -1,12 +1,12 @@
 # Codebuff
 
-Codebuff is a tool for editing codebases via natural-language instructions to Buffy (an expert AI programming assistant).
+Codebuff is an advanced coding agent with a composable agent framework. It also includes:
+- freebuff, the free coding agent
+- evalbuff, a project to improve an agent through evals
 
-## Goals
+## Goal
 
-- Make expert engineers faster (power-user focus).
-- Reduce time/effort for common programming tasks.
-- Improve via iteration/feedback (learn/adapt from usage).
+Make an efficient learning agent that can do anything.
 
 ## Key Technologies
 
@@ -24,20 +24,13 @@ Codebuff is a tool for editing codebases via natural-language instructions to Bu
 - `common/` — shared types, tools, schemas, utilities
 - `agents/` — main agents shipped with codebuff
 - `.agents/` — local agent templates (prompt + programmatic agents)
-
-## Request Flow
-
-1. CLI/SDK sends user input + context to the Codebuff web API.
-2. Agent runtime streams events/chunks back through SDK callbacks.
-3. Tools execute locally (file edits, terminal commands, search) to satisfy tool calls.
+- `freebuff/` - a free coding agent built from configuring codebuff cli
+- `evalbuff/` — automated docs optimization loop (run agent → judge → analyze → improve docs)
 
 ## Conventions
 
-- Prefer `ErrorOr<T>` return values (`success(...)`/`failure(...)` in `common/src/util/error.ts`) over throwing.
 - Never force-push `main` unless explicitly requested.
-- To exclude files from a commit: stage only what you want (`git add <paths>`). Never use `git restore`/`git checkout HEAD -- <file>` to "uncommit" changes.
 - Run interactive git commands in tmux (anything that opens an editor or prompts).
-- Referral codes are applied via the CLI (web onboarding only instructs the user); see `web/src/app/api/referrals/helpers.ts`.
 
 ## Docs
 
@@ -48,3 +41,4 @@ Codebuff is a tool for editing codebases via natural-language instructions to Bu
 - [`docs/testing.md`](docs/testing.md) — DI over mocking, tmux CLI testing
 - [`docs/environment-variables.md`](docs/environment-variables.md) — Env var rules, DI helpers, loading order
 - [`docs/agents-and-tools.md`](docs/agents-and-tools.md) — Agent system, shell shims, tool definitions
+- [`docs/patterns/handle-steps-generators.md`](docs/patterns/handle-steps-generators.md) — handleSteps generator patterns and spawn_agents tool calls

docs/patterns/handle-steps-generators.md

@@ -0,0 +1,180 @@
+# handleSteps Generator Pattern for Programmatic Agents
+
+When creating agents that use `handleSteps` generators to programmatically execute tool calls, follow these exact patterns to avoid TypeScript compilation errors.
+
+## Correct handleSteps Signature
+
+```typescript
+import type { AgentDefinition } from '../types/agent-definition'
+
+const definition: AgentDefinition = {
+  // ... other fields
+
+  handleSteps: function* ({ agentState, prompt, params }) {
+    // Generator body
+  },
+}
+```
+
+## Yielding Tool Calls
+
+Yield objects with `toolName` and `input` properties. The input schema must match the tool's expected parameters exactly.
+
+### spawn_agents Tool
+
+```typescript
+handleSteps: function* ({ agentState, prompt, params }) {
+  const promptWithDefault = prompt ?? 'Default prompt'
+
+  yield {
+    toolName: 'spawn_agents',
+    input: {
+      agents: [
+        {
+          agent_type: 'agent-id-1',
+          prompt: promptWithDefault,
+        },
+        {
+          agent_type: 'agent-id-2', 
+          prompt: promptWithDefault,
+        },
+      ],
+    },
+  }
+
+  // After tool execution, yield 'STEP' to let the agent process results
+  yield 'STEP'
+},
+```
+
+### Common Mistakes
+
+**WRONG:** Using incorrect property names or nested structures
+```typescript
+// ❌ Incorrect - wrong tool call structure
+yield {
+  type: 'tool_call',
+  name: 'spawn_agents',
+  arguments: { ... }
+}
+```
+
+**WRONG:** Using `think_deeply` or custom tool names that don't exist
+```typescript
+// ❌ Incorrect - this tool doesn't exist
+yield {
+  toolName: 'think_deeply',
+  input: { ... }
+}
+```
+
+**CORRECT:** Use `toolName` and `input` at the top level
+```typescript
+// ✅ Correct
+yield {
+  toolName: 'spawn_agents',
+  input: {
+    agents: [{ agent_type: 'my-agent', prompt: 'Do something' }]
+  }
+}
+```
+
+## Yielding STEP
+
+After yielding tool calls, yield the string `'STEP'` to let the main agent process the results:
+
+```typescript
+handleSteps: function* ({ prompt }) {
+  yield {
+    toolName: 'spawn_agents',
+    input: { agents: [...] },
+  }
+
+  // This tells the runtime to run an LLM step to process spawn results
+  yield 'STEP'
+},
+```
+
+## Agent Definition Requirements for Spawning
+
+Agents that spawn sub-agents must include:
+
+1. `toolNames: ['spawn_agents']` - Enable the spawn tool
+2. `spawnableAgents: ['agent-id-1', 'agent-id-2']` - List allowed sub-agents
+
+```typescript
+const definition: AgentDefinition = {
+  id: 'coordinator',
+  model: 'openai/gpt-5',
+  toolNames: ['spawn_agents'],
+  spawnableAgents: ['sub-agent-1', 'sub-agent-2', 'sub-agent-3'],
+  // ...
+}
+```
+
+## Complete Example: Multi-Model Coordinator
+
+See `.agents/deep-thinking/deep-thinker.ts` for a working example:
+
+```typescript
+import type { AgentDefinition } from '../types/agent-definition'
+
+const definition: AgentDefinition = {
+  id: 'deep-thinker',
+  displayName: 'Deep Thinker Agent',
+  model: 'openai/gpt-5',
+
+  toolNames: ['spawn_agents'],
+  spawnableAgents: ['gpt5-thinker', 'sonnet-thinker', 'gemini-thinker'],
+
+  inputSchema: {
+    prompt: {
+      type: 'string',
+      description: 'The topic to analyze',
+    },
+  },
+
+  outputMode: 'last_message',
+
+  handleSteps: function* ({ prompt }) {
+    const promptWithDefault = prompt ?? 'Think about this topic'
+
+    yield {
+      toolName: 'spawn_agents',
+      input: {
+        agents: [
+          { agent_type: 'gpt5-thinker', prompt: promptWithDefault },
+          { agent_type: 'sonnet-thinker', prompt: promptWithDefault },
+          { agent_type: 'gemini-thinker', prompt: promptWithDefault },
+        ],
+      },
+    }
+
+    yield 'STEP'
+  },
+}
+
+export default definition
+```
+
+## Directory Structure
+
+Place related agents in subdirectories under `.agents/`:
+
+```
+.agents/
+└── deep-thinking/
+    ├── deep-thinker.ts      # Coordinator
+    ├── deepest-thinker.ts   # Meta-coordinator  
+    ├── gpt5-thinker.ts      # Sub-agent
+    ├── sonnet-thinker.ts    # Sub-agent
+    └── gemini-thinker.ts    # Sub-agent
+```
+
+## Avoid Over-Engineering
+
+When implementing agents:
+- Only create files that are directly requested
+- Don't add documentation files unless explicitly asked
+- Keep agent definitions simple - use `AgentDefinition` type, not custom wrappers
+- Don't create factory patterns unless there's clear reuse need