add subagent system prompt to chat history file for debugging

Author: sidwan02

packages/core/src/agents/executor.ts

@@ -110,6 +110,7 @@ export class AgentExecutor<TOutput extends z.ZodTypeAny> {
   private readonly compressionService: ChatCompressionService;
   private readonly summarizationService: SummarizationService;
   private hasFailedCompressionAttempt = false;
+  private systemInstruction?: string;
 
   /**
    * Creates and validates a new `AgentExecutor` instance.
@@ -174,6 +175,9 @@ export class AgentExecutor<TOutput extends z.ZodTypeAny> {
   ): Promise<void> {
     const history = await chat.getHistory();
     let fileContent = 'Chat History\n\n';
+    if (this.systemInstruction) {
+      fileContent += `--- ROLE: system ---\n${this.systemInstruction}\n---\n\n`;
+    }
     for (const message of history) {
       let content = '';
       for (const part of message?.parts ?? []) {
@@ -1085,34 +1089,34 @@ export class AgentExecutor<TOutput extends z.ZodTypeAny> {
     );
 
     // Build system instruction from the templated prompt string.
-    const systemInstruction = promptConfig.systemPrompt
+    this.systemInstruction = promptConfig.systemPrompt
       ? await this.buildSystemPrompt(inputs)
       : undefined;
 
     await fs.writeFile(
       `${this.definition.name}_prompt.txt`,
-      systemInstruction ?? '',
+      this.systemInstruction ?? '',
     );
     debugLogger.log(
       `[DEBUG] System Instruction saved to ${this.definition.name}_prompt.txt`,
     );
 
     // debugLogger.log(
-    //   `[AgentExecutor] Created system instruction: ${systemInstruction}`,
+    //   `[AgentExecutor] Created system instruction: ${this.systemInstruction}`,
     // );
 
     if ('host' in modelConfig) {
       const populatedPromptConfig: PromptConfig = {
         ...promptConfig,
-        systemPrompt: systemInstruction ?? '',
+        systemPrompt: this.systemInstruction ?? '',
         directive: this.definition.promptConfig.directive,
         query: this.definition.promptConfig.query
           ? templateString(this.definition.promptConfig.query, inputs)
           : 'Get Started!',
       };
       return new OllamaChat(
         modelConfig as OllamaModelConfig,
-        systemInstruction,
+        this.systemInstruction,
         startHistory,
         populatedPromptConfig,
       );
@@ -1127,8 +1131,8 @@ export class AgentExecutor<TOutput extends z.ZodTypeAny> {
           },
         };
 
-        if (systemInstruction) {
-          generationConfig.systemInstruction = systemInstruction;
+        if (this.systemInstruction) {
+          generationConfig.systemInstruction = this.systemInstruction;
         }
 
         return new GeminiChat(

prompt.txt

@@ -484,4 +484,96 @@ comments.
 
 Use hyphens instead of underscores in flag names (e.g. `my-flag` instead of
 `my_flag`).
---- End of Context from: GEMINI.md ---
+--- End of Context from: GEMINI.md ---
+
+--- Context from: litellm/GEMINI.md ---
+# GEMINI.md
+
+This file provides guidance to Gemini when working with code in this repository.
+
+## Development Commands
+
+### Installation
+- `make install-dev` - Install core development dependencies
+- `make install-proxy-dev` - Install proxy development dependencies with full feature set
+- `make install-test-deps` - Install all test dependencies
+
+### Testing
+- `make test` - Run all tests
+- `make test-unit` - Run unit tests (tests/test_litellm) with 4 parallel workers
+- `make test-integration` - Run integration tests (excludes unit tests)
+- `pytest tests/` - Direct pytest execution
+
+### Code Quality
+- `make lint` - Run all linting (Ruff, MyPy, Black, circular imports, import safety)
+- `make format` - Apply Black code formatting
+- `make lint-ruff` - Run Ruff linting only
+- `make lint-mypy` - Run MyPy type checking only
+
+### Single Test Files
+- `poetry run pytest tests/path/to/test_file.py -v` - Run specific test file
+- `poetry run pytest tests/path/to/test_file.py::test_function -v` - Run specific test
+
+## Architecture Overview
+
+LiteLLM is a unified interface for 100+ LLM providers with two main components:
+
+### Core Library (`litellm/`)
+- **Main entry point**: `litellm/main.py` - Contains core completion() function
+- **Provider implementations**: `litellm/llms/` - Each provider has its own subdirectory
+- **Router system**: `litellm/router.py` + `litellm/router_utils/` - Load balancing and fallback logic
+- **Type definitions**: `litellm/types/` - Pydantic models and type hints
+- **Integrations**: `litellm/integrations/` - Third-party observability, caching, logging
+- **Caching**: `litellm/caching/` - Multiple cache backends (Redis, in-memory, S3, etc.)
+
+### Proxy Server (`litellm/proxy/`)
+- **Main server**: `proxy_server.py` - FastAPI application
+- **Authentication**: `auth/` - API key management, JWT, OAuth2
+- **Database**: `db/` - Prisma ORM with PostgreSQL/SQLite support
+- **Management endpoints**: `management_endpoints/` - Admin APIs for keys, teams, models
+- **Pass-through endpoints**: `pass_through_endpoints/` - Provider-specific API forwarding
+- **Guardrails**: `guardrails/` - Safety and content filtering hooks
+- **UI Dashboard**: Served from `_experimental/out/` (Next.js build)
+
+## Key Patterns
+
+### Provider Implementation
+- Providers inherit from base classes in `litellm/llms/base.py`
+- Each provider has transformation functions for input/output formatting
+- Support both sync and async operations
+- Handle streaming responses and function calling
+
+### Error Handling
+- Provider-specific exceptions mapped to OpenAI-compatible errors
+- Fallback logic handled by Router system
+- Comprehensive logging through `litellm/_logging.py`
+
+### Configuration
+- YAML config files for proxy server (see `proxy/example_config_yaml/`)
+- Environment variables for API keys and settings
+- Database schema managed via Prisma (`proxy/schema.prisma`)
+
+## Development Notes
+
+### Code Style
+- Uses Black formatter, Ruff linter, MyPy type checker
+- Pydantic v2 for data validation
+- Async/await patterns throughout
+- Type hints required for all public APIs
+
+### Testing Strategy
+- Unit tests in `tests/test_litellm/`
+- Integration tests for each provider in `tests/llm_translation/`
+- Proxy tests in `tests/proxy_unit_tests/`
+- Load tests in `tests/load_tests/`
+
+### Database Migrations
+- Prisma handles schema migrations
+- Migration files auto-generated with `prisma migrate dev`
+- Always test migrations against both PostgreSQL and SQLite
+
+### Enterprise Features
+- Enterprise-specific code in `enterprise/` directory
+- Optional features enabled via environment variables
+- Separate licensing and authentication for enterprise features
+--- End of Context from: litellm/GEMINI.md ---

understand.md

@@ -248,9 +248,6 @@ Using the codebase investigator: tell me how the ollama inference works.
    environment either due to prompt forgetting)
 1. Gemma often forgets which files it's already looked at.
 
-1. executor.ts when saving chat history also save the system prompt. Call save
-   chat history to file multiple times in the while loop so it updates with the
-   terminal.
 1. Look at chat_history.txt. despite having a summary it still sees status 0 and
    decidesit doesn't have the full information.