feat(core): Enable generalist agent (#19665)

packages/core/src/agents/generalist-agent.ts

@@ -24,8 +24,7 @@ export const GeneralistAgent = (
   name: 'generalist',
   displayName: 'Generalist Agent',
   description:
-    "A general-purpose AI agent with access to all tools. Use it for complex tasks that don't fit into other specialized agents.",
-  experimental: true,
+    'A general-purpose AI agent with access to all tools. Highly recommended for tasks that are turn-intensive or involve processing large amounts of data. Use this to keep the main session history lean and efficient. Excellent for: batch refactoring/error fixing across multiple files, running commands with high-volume output, and speculative investigations.',
   inputConfig: {
     inputSchema: {
       type: 'object',

packages/core/src/agents/registry.test.ts

@@ -50,6 +50,7 @@ function makeMockedConfig(params?: Partial<ConfigParameters>): Config {
   } as unknown as ToolRegistry);
   vi.spyOn(config, 'getAgentRegistry').mockReturnValue({
     getDirectoryContext: () => 'mock directory context',
+    getAllDefinitions: () => [],
   } as unknown as AgentRegistry);
   return config;
 }
@@ -262,6 +263,7 @@ describe('AgentRegistry', () => {
           overrides: {
             codebase_investigator: { enabled: false },
             cli_help: { enabled: false },
+            generalist: { enabled: false },
           },
         },
       });
@@ -299,13 +301,13 @@ describe('AgentRegistry', () => {
       expect(registry.getDefinition('cli_help')).toBeUndefined();
     });
 
-    it('should NOT register generalist agent by default (because it is experimental)', async () => {
+    it('should register generalist agent by default', async () => {
       const config = makeMockedConfig();
       const registry = new TestableAgentRegistry(config);
 
       await registry.initialize();
 
-      expect(registry.getDefinition('generalist')).toBeUndefined();
+      expect(registry.getDefinition('generalist')).toBeDefined();
     });
 
     it('should register generalist agent if explicitly enabled via override', async () => {

packages/core/src/core/__snapshots__/prompts.test.ts.snap

@@ -57,6 +57,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -209,6 +221,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -480,6 +504,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -632,6 +668,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -1506,6 +1554,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -1657,6 +1717,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -1800,6 +1872,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -1943,6 +2027,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -2082,6 +2178,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -2221,6 +2329,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -2352,6 +2472,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -2490,6 +2622,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>test-agent</name>
@@ -2870,6 +3014,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -3009,6 +3165,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -3260,6 +3428,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>
@@ -3399,6 +3579,18 @@ Use the following guidelines to optimize your search and read patterns.
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
   <subagent>
     <name>mock-agent</name>

packages/core/src/prompts/snippets.ts

@@ -228,6 +228,18 @@ export function renderSubAgents(subAgents?: SubAgentOptions[]): string {
 
 Sub-agents are specialized expert agents. Each sub-agent is available as a tool of the same name. You MUST delegate tasks to the sub-agent with the most relevant expertise.
 
+### Strategic Orchestration & Delegation
+Operate as a **strategic orchestrator**. Your own context window is your most precious resource. Every turn you take adds to the permanent session history. To keep the session fast and efficient, use sub-agents to "compress" complex or repetitive work.
+
+When you delegate, the sub-agent's entire execution is consolidated into a single summary in your history, keeping your main loop lean.
+
+**High-Impact Delegation Candidates:**
+- **Repetitive Batch Tasks:** Tasks involving more than 3 files or repeated steps (e.g., "Add license headers to all files in src/", "Fix all lint errors in the project").
+- **High-Volume Output:** Commands or tools expected to return large amounts of data (e.g., verbose builds, exhaustive file searches).
+- **Speculative Research:** Investigations that require many "trial and error" steps before a clear path is found.
+
+**Assertive Action:** Continue to handle "surgical" tasks directly—simple reads, single-file edits, or direct questions that can be resolved in 1-2 turns. Delegation is an efficiency tool, not a way to avoid direct action when it is the fastest path.
+
 <available_subagents>
 ${subAgentsXml}
 </available_subagents>