Rename commander/commander-lite to basher

jahooma · jahooma · commit 95aa78bb502e · 2026-03-15T15:05:31.000-07:00
diff --git a/agents/__tests__/basher.test.ts b/agents/__tests__/basher.test.ts
@@ -1,6 +1,6 @@
 import { describe, test, expect } from 'bun:test'
 
-import commander from '../commander'
+import commander from '../basher'
 
 import type { AgentState } from '../types/agent-definition'
 import type { ToolResultOutput } from '../types/util-types'
@@ -19,11 +19,11 @@ describe('commander agent', () => {
 
   describe('definition', () => {
     test('has correct id', () => {
-      expect(commander.id).toBe('commander')
+      expect(commander.id).toBe('basher')
     })
 
     test('has display name', () => {
-      expect(commander.displayName).toBe('Commander')
+      expect(commander.displayName).toBe('Basher')
     })
 
     test('uses flash-lite model', () => {
diff --git a/agents/base2/base-deep.ts b/agents/base2/base-deep.ts
@@ -32,7 +32,7 @@ Use the spawn_agents tool to spawn specialized agents to help you complete the u
   - Spawn the thinker-gpt after gathering context to solve complex problems or when the user asks you to think about a problem. (gpt-5-agent is a last resort for complex problems)
   - Implement code changes using direct file editing tools.
   - Prefer apply_patch for existing-file edits. Use write_file only for creating or replacing entire files when that is simpler.
-  - Spawn commanders sequentially if the second command depends on the the first.
+  - Spawn bashers sequentially if the second command depends on the the first.
 - **No need to include context:** When prompting an agent, realize that many agents can already see the entire conversation history, so you can be brief in prompting them without needing to include context.
 - **Never spawn the context-pruner agent:** This agent is spawned automatically for you and you don't need to spawn it yourself.
 
@@ -199,7 +199,7 @@ Iteratively review until the code is clean:
 
 Thoroughly validate the changes:
 
-1. Run any existing unit tests that cover the modified code (spawn commanders in parallel for typechecks, tests, lints as appropriate).
+1. Run any existing unit tests that cover the modified code (spawn bashers in parallel for typechecks, tests, lints as appropriate).
 2. Write and run additional unit tests for new functionality. Fix any test failures.
 3. You MUST attempt end-to-end verification: use tools to run the actual application (or equivalent) and verify the changes work in practice. For example:
    - For a web app: start the server and check the relevant endpoints
@@ -298,7 +298,7 @@ export function createBaseDeep(options?: {
       'glob-matcher',
       'researcher-web',
       'researcher-docs',
-      'commander',
+      'basher',
       'thinker-gpt',
       'code-reviewer-gpt',
       'gpt-5-agent',
diff --git a/agents/base2/base2.ts b/agents/base2/base2.ts
@@ -76,7 +76,7 @@ export function createBase2(
       isMax && 'file-picker-max',
       'researcher-web',
       'researcher-docs',
-      isFree ? 'commander-lite' : 'commander',
+      'basher',
       isDefault && 'thinker',
       (isDefault || isMax) && ['opus-agent', 'gpt-5-agent'],
       isMax && 'thinker-best-of-n-opus',
@@ -125,7 +125,7 @@ export function createBase2(
     - Create an impressive demonstration showcasing web development capabilities
 -  **Refactoring Awareness:** Whenever you modify an exported symbol like a function or class or variable, you should find and update all the references to it appropriately using the code_search tool.
 -  **Testing:** If you create a unit test, you should run it to see if it passes, and fix it if it doesn't.
--  **Package Management:** When adding new packages, use the commander agent to install the package rather than editing the package.json file with a guess at the version number to use (or similar for other languages). This way, you will be sure to have the latest version of the package. Do not install packages globally unless asked by the user (e.g. Don't run \`npm install -g <package-name>\`). Always try to use the package manager associated with the project (e.g. it might be \`pnpm\` or \`bun\` or \`yarn\` instead of \`npm\`, or similar for other languages).
+-  **Package Management:** When adding new packages, use the basher agent to install the package rather than editing the package.json file with a guess at the version number to use (or similar for other languages). This way, you will be sure to have the latest version of the package. Do not install packages globally unless asked by the user (e.g. Don't run \`npm install -g <package-name>\`). Always try to use the package manager associated with the project (e.g. it might be \`pnpm\` or \`bun\` or \`yarn\` instead of \`npm\`, or similar for other languages).
 -  **Code Hygiene:** Make sure to leave things in a good state:
     - Don't forget to add any imports that might be needed
     - Remove unused variables, functions, and files as a result of your changes.
@@ -152,7 +152,7 @@ Use the spawn_agents tool to spawn specialized agents to help you complete the u
         '- Implement code changes using the str_replace or write_file tools directly.',
         isFree &&
         '- Spawn a code-reviewer-lite to review the changes after you have implemented the changes.',
-        '- Spawn commanders sequentially if the second command depends on the the first.',
+        '- Spawn bashers sequentially if the second command depends on the the first.',
         isDefault &&
         '- Spawn a code-reviewer to review the changes after you have implemented the changes.',
         isMax &&
@@ -213,12 +213,12 @@ ${isDefault
       }
 
 ${isDefault
-        ? `[ You spawn a code-reviewer, a commander to typecheck the changes, and another commander to run tests, all in parallel ]`
+        ? `[ You spawn a code-reviewer, a basher to typecheck the changes, and another basher to run tests, all in parallel ]`
         : isFree
-          ? `[ You spawn a code-reviewer-lite to review the changes, and a commander to typecheck the changes, and another commander to run tests, all in parallel ]`
+          ? `[ You spawn a code-reviewer-lite to review the changes, and a basher to typecheck the changes, and another basher to run tests, all in parallel ]`
           : isMax
-            ? `[  You spawn a commander to typecheck the changes, and another commander to run tests, in parallel. Then, you spawn a code-reviewer-multi-prompt to review the changes. ]`
-            : '[ You spawn a commander to typecheck the changes and another commander to run tests, all in parallel ]'
+            ? `[  You spawn a basher to typecheck the changes, and another basher to run tests, in parallel. Then, you spawn a code-reviewer-multi-prompt to review the changes. ]`
+            : '[ You spawn a basher to typecheck the changes and another basher to run tests, all in parallel ]'
       }
 
 ${isDefault
@@ -227,7 +227,7 @@ ${isDefault
           ? `[ You fix the issues found by the code-reviewer-lite and type/test errors ]`
           : isMax
             ? `[ You fix the issues found by the code-reviewer-multi-prompt and type/test errors ]`
-            : '[ You fix the issues found by the type/test errors and spawn more commanders to confirm ]'
+            : '[ You fix the issues found by the type/test errors and spawn more bashers to confirm ]'
       }
 
 [ All tests & typechecks pass -- you write a very short final summary of the changes you made ]
@@ -298,7 +298,7 @@ ${PLACEHOLDER.GIT_CHANGES_PROMPT}
   }
 }
 
-const EXPLORE_PROMPT = `- Iteratively spawn file pickers, commanders, and web/docs researchers to gather context as needed. Use the code_search, list_directory, and glob tools directly for searching and exploring the codebase. The file-picker agent in particular is very useful to find relevant files -- try spawning multiple in parallel (say, 2-5) to explore different parts of the codebase. Use read_subtree if you need to grok a particular part of the codebase. Read all the relevant files using the read_files tool.`
+const EXPLORE_PROMPT = `- Iteratively spawn file pickers, bashers, and web/docs researchers to gather context as needed. Use the code_search, list_directory, and glob tools directly for searching and exploring the codebase. The file-picker agent in particular is very useful to find relevant files -- try spawning multiple in parallel (say, 2-5) to explore different parts of the codebase. Use read_subtree if you need to grok a particular part of the codebase. Read all the relevant files using the read_files tool.`
 
 function buildImplementationInstructionsPrompt({
   isSonnet,
diff --git a/agents/basher.ts b/agents/basher.ts
@@ -5,13 +5,13 @@ import type {
   AgentStepContext,
 } from './types/agent-definition'
 
-const commander: AgentDefinition = {
-  id: 'commander',
+const basher: AgentDefinition = {
+  id: 'basher',
   publisher,
   model: 'google/gemini-3.1-flash-lite-preview',
-  displayName: 'Commander',
+  displayName: 'Basher',
   spawnerPrompt:
-    'Runs a single terminal command and describes its output using an LLM based on what information is requested.',
+    'Runs a single terminal command and describes its output using an LLM. A lightweight shell command executor.',
 
   inputSchema: {
     prompt: {
@@ -64,7 +64,7 @@ Do not use any tools! Only analyze the output of the command.`,
     const command = params?.command as string | undefined
     if (!command) {
       // Using console.error because agents run in a sandboxed environment without access to structured logger
-      console.error('Commander agent: missing required "command" parameter')
+      console.error('Basher agent: missing required "command" parameter')
       yield {
         toolName: 'set_output',
         input: { output: 'Error: Missing required "command" parameter' },
@@ -102,4 +102,4 @@ Do not use any tools! Only analyze the output of the command.`,
   },
 }
 
-export default commander
+export default basher
diff --git a/agents/commander-lite.ts b/agents/commander-lite.ts
diff --git a/agents/context-pruner.ts b/agents/context-pruner.ts
@@ -299,8 +299,7 @@ const definition: AgentDefinition = {
       'file-picker',
       'researcher-web',
       'researcher-docs',
-      'commander',
-      'commander-lite',
+      'basher',
       'code-reviewer',
       'code-reviewer-multi-prompt',
     ]
diff --git a/agents/general-agent/general-agent.ts b/agents/general-agent/general-agent.ts
@@ -56,7 +56,7 @@ export const createGeneralAgent = (options: {
       'code-searcher',
       'directory-lister',
       'glob-matcher',
-      'commander',
+      'basher',
       'context-pruner',
     ),
     toolNames: [
@@ -69,7 +69,7 @@ export const createGeneralAgent = (options: {
 
     instructionsPrompt: buildArray(
       `Use the spawn_agents tool to spawn agents to help you complete the user request.`,
-      !isGpt5 && `If you need to find more information in the codebase, file-picker is really good at finding relevant files. You should spawn multiple agents in parallel when possible to speed up the process. (e.g. spawn 3 file-pickers + 1 code-searcher + 1 researcher-web in one spawn_agents call or 3 commanders in one spawn_agents call).`,
+      !isGpt5 && `If you need to find more information in the codebase, file-picker is really good at finding relevant files. You should spawn multiple agents in parallel when possible to speed up the process. (e.g. spawn 3 file-pickers + 1 code-searcher + 1 researcher-web in one spawn_agents call or 3 bashers in one spawn_agents call).`,
     ).join('\n'),
 
     handleSteps: function* ({ params }) {
diff --git a/cli/src/utils/constants.ts b/cli/src/utils/constants.ts
@@ -37,8 +37,7 @@ export const COLLAPSED_BY_DEFAULT_AGENT_IDS = [
   'code-reviewer-selector',
   'thinker-selector',
   'best-of-n-selector',
-  'commander',
-  'commander-lite',
+  'basher',
   'code-searcher',
   'directory-lister',
   'glob-matcher',
diff --git a/cli/src/utils/sdk-event-handlers.ts b/cli/src/utils/sdk-event-handlers.ts
@@ -371,7 +371,7 @@ const updateSpawnAgentBlocks = (
 
       if (result?.value) {
         const { content, hasError } = extractSpawnAgentResultContent(result.value)
-        // Preserve streamed content (agents like commander stream their output)
+        // Preserve streamed content (agents like basher stream their output)
         const hasStreamedContent = block.blocks.length > 0
         if (hasError || content || hasStreamedContent) {
           return {
diff --git a/common/src/constants/free-agents.ts b/common/src/constants/free-agents.ts
@@ -30,7 +30,7 @@ export const FREE_MODE_AGENT_MODELS: Record<string, Set<string>> = {
   'researcher-docs': new Set(['google/gemini-3.1-flash-lite-preview']),
 
   // Command execution
-  'commander-lite': new Set(['google/gemini-3.1-flash-lite-preview']),
+  'basher': new Set(['google/gemini-3.1-flash-lite-preview']),
 
   // Editor for free mode
   'editor-lite': new Set(['minimax/minimax-m2.5']),
diff --git a/common/src/tools/params/tool/spawn-agents.ts b/common/src/tools/params/tool/spawn-agents.ts
@@ -37,11 +37,11 @@ The prompt field is a simple string, while params is a JSON object that gets val
 
 Each agent available is already defined as another tool, or, dynamically defined later in the conversation.
 
-**IMPORTANT**: \`agent_type\` must be an actual agent name (e.g., \`commander\`, \`code-searcher\`, \`opus-agent\`), NOT a tool name like \`read_files\`, \`str_replace\`, \`code_search\`, etc. If you need to call a tool, use it directly as a tool call instead of wrapping it in spawn_agents.
+**IMPORTANT**: \`agent_type\` must be an actual agent name (e.g., \`basher\`, \`code-searcher\`, \`opus-agent\`), NOT a tool name like \`read_files\`, \`str_replace\`, \`code_search\`, etc. If you need to call a tool, use it directly as a tool call instead of wrapping it in spawn_agents.
 
 You can call agents either as direct tool calls (e.g., \`example-agent\`) or use \`spawn_agents\`. Both formats work, but **prefer using spawn_agents** because it allows you to spawn multiple agents in parallel for better performance. Both use the same schema with nested \`prompt\` and \`params\` fields.
 
-**IMPORTANT**: Many agents have REQUIRED fields in their params schema. Check the agent's schema before spawning - if params has required fields, you MUST include them in the params object. For example, code-searcher requires \`searchQueries\`, commander requires \`command\`.
+**IMPORTANT**: Many agents have REQUIRED fields in their params schema. Check the agent's schema before spawning - if params has required fields, you MUST include them in the params object. For example, code-searcher requires \`searchQueries\`, basher requires \`command\`.
 
 Example:
 ${$getNativeToolCallExampleString({
@@ -50,7 +50,7 @@ ${$getNativeToolCallExampleString({
   input: {
     agents: [
       {
-        agent_type: 'commander',
+        agent_type: 'basher',
         prompt: 'Check if tests pass',
         params: {
           command: 'npm test',
diff --git a/docs/architecture.md b/docs/architecture.md
@@ -92,7 +92,7 @@ Prompt-based and programmatic agent definitions that ship with Codebuff.
   - `reviewer/` — Code review agent with multi-prompt variant
   - `researcher/` — Web search and docs search agents
   - `general-agent/` — General-purpose agents (opus-agent, gpt-5-agent)
-  - `commander.ts` / `commander-lite.ts` — Terminal command execution agents
+  - `basher.ts` — Terminal command execution agent (id: 'basher', displayName: 'Basher')
   - `context-pruner.ts` — Conversation summarization to manage context length
 - **Depends on:** `common` (for agent definition types and tool params)
 
diff --git a/packages/agent-runtime/src/tools/handlers/tool/spawn-agent-utils.ts b/packages/agent-runtime/src/tools/handlers/tool/spawn-agent-utils.ts
@@ -162,70 +162,6 @@ export function getMatchingSpawn(
   return null
 }
 
-/**
- * Synchronously transforms spawn_agents input to use 'commander-lite' instead of 'commander'
- * when the parent agent doesn't have access to 'commander' but does have access to 'commander-lite'.
- * This should be called BEFORE the tool call is streamed to the UI.
- */
-export function transformSpawnAgentsInput(
-  input: Record<string, unknown>,
-  spawnableAgents: AgentTemplateType[],
-): Record<string, unknown> {
-  const agents = input.agents
-  if (!Array.isArray(agents)) {
-    return input
-  }
-
-  let hasTransformation = false
-  const transformedAgents = agents.map((agent) => {
-    if (typeof agent !== 'object' || agent === null) {
-      return agent
-    }
-
-    const agentEntry = agent as Record<string, unknown>
-    const agentTypeStr = agentEntry.agent_type
-    if (typeof agentTypeStr !== 'string') {
-      return agent
-    }
-
-    // Check if this is 'commander'
-    const { agentId } = parseAgentId(agentTypeStr)
-    if (agentId !== 'commander') {
-      return agent
-    }
-
-    // Check if 'commander' is available in spawnableAgents
-    const commanderType = getMatchingSpawn(spawnableAgents, agentTypeStr)
-    if (commanderType) {
-      // Commander is available, no transformation needed
-      return agent
-    }
-
-    // Check if 'commander-lite' is available as a fallback
-    const commanderLiteType = getMatchingSpawn(spawnableAgents, 'commander-lite')
-    if (!commanderLiteType) {
-      // Neither available, let validation handle the error
-      return agent
-    }
-
-    // Transform commander -> commander-lite
-    hasTransformation = true
-    return {
-      ...agentEntry,
-      agent_type: commanderLiteType,
-    }
-  })
-
-  if (!hasTransformation) {
-    return input
-  }
-
-  return {
-    ...input,
-    agents: transformedAgents,
-  }
-}
-
 /**
  * Validates agent template and permissions
  */
diff --git a/packages/agent-runtime/src/tools/tool-executor.ts b/packages/agent-runtime/src/tools/tool-executor.ts
@@ -9,7 +9,6 @@ import { getAgentShortName } from '../templates/prompts'
 import { codebuffToolHandlers } from './handlers/list'
 import {
   getMatchingSpawn,
-  transformSpawnAgentsInput,
 } from './handlers/tool/spawn-agent-utils'
 import { getAgentTemplate } from '../templates/agent-registry'
 import { ensureZodSchema } from './prompts'
@@ -192,18 +191,11 @@ export async function executeToolCall<T extends ToolName>(
     return previousToolCallFinished
   }
 
-  // Transform spawn_agents input to use commander-lite fallback before streaming
-  // This ensures the UI shows the correct agent type from the start
-  const transformedInput =
-    toolName === 'spawn_agents'
-      ? transformSpawnAgentsInput(input, agentTemplate.spawnableAgents)
-      : input
-
   // TODO: Allow tools to provide a validation function, and move this logic into the spawn_agents validation function.
   // Pre-validate spawn_agents to filter out non-existent agents before streaming
-  let effectiveInput = transformedInput
+  let effectiveInput = input
   if (toolName === 'spawn_agents') {
-    const agents = (transformedInput as Record<string, unknown>).agents
+    const agents = (input as Record<string, unknown>).agents
     if (Array.isArray(agents)) {
       const BASE_AGENTS = [
         'base',
@@ -284,7 +276,7 @@ export async function executeToolCall<T extends ToolName>(
         }
         const errorMsg = `Some agents could not be spawned: ${errors.join('; ')}. Proceeding with valid agents only.`
         onResponseChunk({ type: 'error', message: errorMsg })
-        effectiveInput = { ...transformedInput, agents: validAgents }
+        effectiveInput = { ...input, agents: validAgents }
       }
     }
   }
diff --git a/web/src/content/advanced/how-does-it-work.mdx b/web/src/content/advanced/how-does-it-work.mdx
@@ -26,7 +26,7 @@ The main agent ("Buffy") runs on Claude Opus 4.6. It reads your prompt, gathers
 - [**Thinker**](/publishers/codebuff/agents/thinker) (GPT-5.1, Gemini 2.5 Pro) - works through hard problems
 - [**Editor**](/publishers/codebuff/agents/editor) (GPT-5.1, Claude Opus 4.6) - writes and modifies code
 - [**Reviewer**](/publishers/codebuff/agents/reviewer) (Claude Opus 4.6, MiniMax M2.5 in Free mode) - catches bugs and style issues
-- [**Commander**](/publishers/codebuff/agents/commander) (Grok 4 Fast or Claude Sonnet 4.5) - runs terminal commands
+- [**Basher**](/publishers/codebuff/agents/basher) (Gemini 3.1 Flash Lite) - runs terminal commands
 
 ## Best-of-N Selection (Max Mode)
 
@@ -38,6 +38,6 @@ In Max mode, Codebuff spawns multiple editors with different strategies. A selec
 2. File pickers and searchers find relevant code
 3. Thinkers analyze the problem if needed
 4. Editors generate changes
-5. Reviewers check for issues; commanders run tests
+5. Reviewers check for issues; bashers run tests
 
 The server is stateless. It streams requests to model providers (Anthropic, OpenAI, Google, xAI) over websockets. Your code stays local; only relevant context is sent.
diff --git a/web/src/content/agents/overview.mdx b/web/src/content/agents/overview.mdx
