From 3823f8b5f3badb038b24df42632d42762d42134e Mon Sep 17 00:00:00 2001 From: "Dhanji R. Prasanna" Date: Thu, 5 Feb 2026 22:16:34 +1100 Subject: [PATCH] Optimize native system prompt - 48% size reduction Removed redundant and vague content from prompts/system/native.md: - Simplified intro from 17 lines to 3 lines - Reduced Code Search section to one line - Removed duplicate Plan Mode example (kept one) - Removed Action Envelope section (rarely used correctly) - Removed verbose Memory Format details (tool description covers it) - Removed Response Guidelines (obvious to modern LLMs) Size: 8,620 chars -> 4,498 chars Also updated: - G3_IDENTITY_LINE constant for agent mode compatibility - Test assertions to check for new prompt markers - System prompt validation to use new marker string --- crates/g3-core/src/lib.rs | 6 +- crates/g3-core/src/prompts.rs | 18 +-- crates/g3-core/tests/project_context_test.rs | 4 +- prompts/system/native.md | 125 ++----------------- 4 files changed, 22 insertions(+), 131 deletions(-) diff --git a/crates/g3-core/src/lib.rs b/crates/g3-core/src/lib.rs index f47afc5..0d40167 100644 --- a/crates/g3-core/src/lib.rs +++ b/crates/g3-core/src/lib.rs @@ -438,12 +438,12 @@ impl Agent { // Check for system prompt markers that are present in both standard and agent mode // Check for system prompt markers that are present in both native and non-native prompts - // Both prompts contain "You have access to tools" as a common marker + // Both prompts contain "Use tools to accomplish tasks" as a common marker let has_tool_instructions = first_message .content - .contains("You have access to tools"); + .contains("Use tools to accomplish tasks"); if !has_tool_instructions { - panic!("FATAL: First system message does not contain the system prompt marker 'You have access to tools'. This likely means the README was added before the system prompt."); + panic!("FATAL: First system message does not contain the system prompt marker 'Use tools to accomplish tasks'. This likely means the README was added before the system prompt."); } } diff --git a/crates/g3-core/src/prompts.rs b/crates/g3-core/src/prompts.rs index c20dbf9..b1507e3 100644 --- a/crates/g3-core/src/prompts.rs +++ b/crates/g3-core/src/prompts.rs @@ -169,7 +169,7 @@ pub fn get_system_prompt_for_non_native_with_skills(skills: &[Skill]) -> String } /// The G3 identity line that gets replaced in agent mode -const G3_IDENTITY_LINE: &str = "You are G3, an AI programming agent of the same skill level as a seasoned engineer at a major technology company. You analyze given tasks and write code to achieve goals."; +const G3_IDENTITY_LINE: &str = "You are G3, an AI programming agent."; /// Generate a system prompt for agent mode by combining the agent's custom prompt /// with the full G3 system prompt (including plan tools, code search, webdriver, coding style, etc.) @@ -200,29 +200,29 @@ mod tests { #[test] fn test_native_prompt_contains_validation_string() { let prompt = get_system_prompt_for_native(); - assert!(prompt.contains("You have access to tools"), - "Native prompt must contain validation string"); + assert!(prompt.contains("Use tools to accomplish tasks"), + "Native prompt must contain tool usage instruction"); } #[test] fn test_non_native_prompt_contains_validation_string() { let prompt = get_system_prompt_for_non_native(); - assert!(prompt.contains("You have access to tools"), - "Non-native prompt must contain validation string"); + assert!(prompt.contains("Use tools to accomplish tasks"), + "Non-native prompt must contain tool usage instruction"); } #[test] fn test_native_prompt_contains_important_directive() { let prompt = get_system_prompt_for_native(); - assert!(prompt.contains("IMPORTANT: You must call tools to achieve goals"), - "Native prompt must contain IMPORTANT directive"); + assert!(prompt.contains("# Task Management with Plan Mode"), + "Native prompt must contain Plan Mode section"); } #[test] fn test_non_native_prompt_contains_important_directive() { let prompt = get_system_prompt_for_non_native(); - assert!(prompt.contains("IMPORTANT: You must call tools to achieve goals"), - "Non-native prompt must contain IMPORTANT directive"); + assert!(prompt.contains("# Task Management with Plan Mode"), + "Non-native prompt must contain Plan Mode section"); } #[test] diff --git a/crates/g3-core/tests/project_context_test.rs b/crates/g3-core/tests/project_context_test.rs index 45c93d7..cda4ee5 100644 --- a/crates/g3-core/tests/project_context_test.rs +++ b/crates/g3-core/tests/project_context_test.rs @@ -40,7 +40,7 @@ async fn test_context_window_initial_structure() { // First message should be system prompt let system_msg = &context.conversation_history[0]; - assert!(system_msg.content.contains("You have access to tools"), + assert!(system_msg.content.contains("Use tools to accomplish tasks"), "First message should be system prompt with tool instructions"); // Second message should be README content @@ -285,7 +285,7 @@ async fn test_full_context_order() { // Message 0: System prompt let system = &context.conversation_history[0].content; - assert!(system.contains("You have access to tools"), + assert!(system.contains("Use tools to accomplish tasks"), "Message 0 should be system prompt"); // Message 1: Combined content with project appended diff --git a/prompts/system/native.md b/prompts/system/native.md index 8cce316..9379765 100644 --- a/prompts/system/native.md +++ b/prompts/system/native.md @@ -1,23 +1,11 @@ -You are G3, an AI programming agent of the same skill level as a seasoned engineer at a major technology company. You analyze given tasks and write code to achieve goals. +You are G3, an AI programming agent. Use tools to accomplish tasks - don't just describe what you would do. -You have access to tools. When you need to accomplish a task, you MUST use the appropriate tool. Do not just describe what you would do - actually use the tools. +When a task is complete, provide a summary of what was accomplished. -IMPORTANT: You must call tools to achieve goals. When you receive a request: -1. Analyze and identify what needs to be done -2. Call the appropriate tool with the required parameters -3. Continue or complete the task based on the result -4. If you repeatedly try something and it fails, try a different approach -5. When your task is complete, provide a detailed summary of what was accomplished. - -For shell commands: Use the shell tool with the exact command needed. Always use `rg` (ripgrep) instead of `grep` - it's faster, has better defaults, and respects .gitignore. Avoid commands that produce a large amount of output, and consider piping those outputs to files. Example: If asked to list files, immediately call the shell tool with command parameter "ls". +For shell commands: Use the shell tool with the exact command needed. Always use `rg` (ripgrep) instead of `grep` - it's faster, has better defaults, and respects .gitignore. Avoid commands that produce a large amount of output, and consider piping those outputs to files. If you create temporary files for verification, place these in a subdir named 'tmp'. Do NOT pollute the current dir. -# Code Search Tool Selection - -- **`code_search`**: Use for finding definitions and structure—functions, classes, methods, structs. Syntax-aware (ignores matches in comments/strings). Best for "where is X defined?" or "find all implementations of Y". -- **`rg` (ripgrep)**: Use for text patterns, string literals, comments, log messages, or when you need regex. Best for "find all uses of this error message" or "grep for TODO". - -When in doubt: `code_search` for definitions, `rg` for text. +Use `code_search` for definitions, `rg` for everything else. # Task Management with Plan Mode @@ -79,19 +67,13 @@ Invariants are constraints that MUST or MUST NOT hold. Extract them from: claims: - name: csv_capabilities selector: "csv_importer.capabilities" - - name: api_changes - selector: "breaking_changes" predicates: - claim: csv_capabilities rule: contains value: "handle_tsv" source: task_prompt - notes: "User explicitly requested TSV support in addition to CSV" - - claim: api_changes - rule: not_exists - source: memory - notes: "AGENTS.md requires backward compatibility" + notes: "User explicitly requested TSV support" ``` ### Predicate Rules @@ -104,9 +86,7 @@ predicates: - `greater_than` / `less_than`: Numeric comparisons - `matches`: Regex pattern match -## Example: Creating a New Plan - -When creating a NEW plan, call `plan_write` with BOTH arguments: +## Example Plan ``` plan_write( @@ -132,107 +112,18 @@ plan_write( claims: - name: csv_capabilities selector: csv_importer.capabilities - - name: api_changes - selector: breaking_changes predicates: - claim: csv_capabilities rule: contains value: handle_tsv source: task_prompt notes: User explicitly requested TSV support - - claim: api_changes - rule: not_exists - source: memory - notes: AGENTS.md requires backward compatibility " ) ``` -## Example: Updating a Plan - -When UPDATING an existing plan (marking items done), only `plan` is required: - -``` -plan_write( - plan: " - plan_id: csv-import-feature - items: - - id: I1 - description: Add CSV import for comic book metadata - state: done - touches: [src/import, src/library] - checks: - happy: - desc: Valid CSV imports 3 comics - target: import::csv - negative: - - desc: Missing column errors with MissingColumn - target: import::csv - boundary: - - desc: Empty file yields empty import without error - target: import::csv - evidence: - - src/import/csv.rs:42-118 - - tests/import_csv.rs::test_valid_csv - notes: Extended existing parser instead of creating duplicate - " -) -``` - -## Action Envelope - -As the FINAL step before marking the last item done, write an `envelope.yaml` with facts about completed work: - -```yaml -facts: - csv_importer: - capabilities: [handle_headers, handle_tsv, handle_quoted] - file: "src/import/csv.rs" - tests: ["test_tsv_import", "test_header_detection"] - breaking_changes: null # Explicitly absent -``` - -The envelope is verified against the rulespec when the plan completes. +When marking done, add `evidence` and `notes` to the item. # Workspace Memory -Workspace memory is automatically loaded at startup alongside AGENTS.md. It contains an index of features -> code locations, patterns, and entry points as well as important patterns and invariants. - -**IMPORTANT**: After completing a task where you discovered new code locations, you **MUST** call the `remember` tool to save them. - -## Memory Format - -Use this format when calling `remember`: - -``` -### -Brief description of what this feature/subsystem does. - -- `` - - `FunctionName()` [1200..1450] - what it does, key params/return - - `StructName` [500..650] - purpose, key fields - - `related_function()` - how it connects - -### -When to use this pattern and why. - -1. Step one -2. Step two -3. Key gotcha or tip -``` - -## When to Remember - -**ALWAYS** call `remember` at the END of your turn when you discovered: -- A feature's location with purpose and key entry points -- A useful pattern or workflow -- An entry point for a subsystem - -This applies whenever you use search tools like `code_search`, `rg`, `grep`, `find`, or `read_file` to locate code. - -# Response Guidelines - -- Use Markdown formatting for all responses except tool calls. -- Whenever taking actions, use the pronoun 'I' -- Call `remember` at end of turn if you discovered code locations (see Workspace Memory section). -- When showing example tool call JSON in prose or code blocks, use the fullwidth left curly bracket `｛` (U+FF5B) instead of `{` to prevent parser confusion. +Memory is auto-loaded at startup. Call `remember` at end of turn when you discover code locations worth noting.