Files
optimclaw/tests/e2e_trace_file_tools.rs
30790439ee perf: build system prompt once per turn, skip tools on force-text (#583)
* perf: build system prompt once per turn, skip tools on force-text, fix nudge role (#565)

Three fixes to agentic loop prompt handling:

1. Build system prompt once per turn instead of every tool iteration.
   `build_system_prompt_with_tools` is now pub; callers pass the result
   via `ReasoningContext::system_prompt` to avoid rebuilding ~1,500 tokens
   per iteration.

2. Skip `## Available Tools` section when `force_text = true`. The
   dispatcher passes a no-tools prompt variant on the final iteration,
   saving ~460 tokens and removing misleading instructions.

3. Change nudge message from `Role::System` to `Role::User`. A second
   system message mid-conversation is unsupported by most providers.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: revert nudge role change to keep ChatMessage::system

Copilot review correctly identified that using Role::User for the nudge
breaks compact_messages_for_retry, which uses rposition for Role::User
to find the last real user message. Role::Assistant would cause
back-to-back assistant messages. Since no production issues were reported
with the original system role, revert to ChatMessage::system.

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: address PR review — omit tool guidance when tools empty, rename shadowed var

- Conditionalize "Call tools…" guidelines and "## Tool Call Style" section
  in the system prompt so they are only included when tools are non-empty.
  Previously the force-text (no-tools) prompt still contained misleading
  tool-calling instructions. (Copilot review comment)

- Rename `system_prompt` → `cached_prompt` in dispatcher to avoid shadowing
  the earlier workspace identity `system_prompt` variable. (Copilot review)

- Add regression tests: `test_system_prompt_with_tools_contains_tool_guidance`
  and extended assertions in `test_system_prompt_without_tools_omits_tools_section`.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
Co-authored-by: [email protected] <[email protected]>
2026-03-07 09:15:00 +00:00

54 lines
1.7 KiB
Rust

//! E2E trace test: validates that the agent can execute `write_file` and
//! `read_file` tool calls driven by a TraceLlm trace.
#[cfg(feature = "libsql")]
mod support;
#[cfg(feature = "libsql")]
mod tests {
use std::time::Duration;
use crate::support::cleanup::CleanupGuard;
use crate::support::test_rig::TestRigBuilder;
use crate::support::trace_llm::LlmTrace;
const TEST_DIR: &str = "/tmp/ironclaw_e2e_test";
const TEST_FILE: &str = "/tmp/ironclaw_e2e_test/hello.txt";
const EXPECTED_CONTENT: &str = "Hello, E2E test!";
fn setup_test_dir() {
let _ = std::fs::remove_dir_all(TEST_DIR);
std::fs::create_dir_all(TEST_DIR).expect("failed to create test directory");
}
#[tokio::test]
async fn test_file_write_and_read_flow() {
setup_test_dir();
let _cleanup = CleanupGuard::new().dir(TEST_DIR);
let fixture_path = concat!(
env!("CARGO_MANIFEST_DIR"),
"/tests/fixtures/llm_traces/file_write_read.json"
);
let trace = LlmTrace::from_file(fixture_path).expect("failed to load trace fixture");
let rig = TestRigBuilder::new()
.with_trace(trace.clone())
.build()
.await;
rig.send_message("Please write a greeting to a file and read it back.")
.await;
let responses = rig.wait_for_responses(1, Duration::from_secs(15)).await;
rig.verify_trace_expects(&trace, &responses);
// Extra: verify file on disk (can't express in expects).
let file_content =
std::fs::read_to_string(TEST_FILE).expect("hello.txt should exist after write_file");
assert_eq!(file_content, EXPECTED_CONTENT);
rig.shutdown();
}
}