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]>

tests/e2e_worker_coverage.rs

@@ -91,17 +91,22 @@ mod tests {
 
     #[tokio::test]
     async fn tool_error_feedback() {
+        // Use a tempdir for the recovery file. The fixture's recovery path
+        // is updated to write here via the test_dir variable.
         let tmp = tempfile::tempdir().expect("create temp dir");
+        let test_dir = tmp.path().to_str().expect("tempdir path");
 
-        let mut trace = LlmTrace::from_file(concat!(
+        // Patch the fixture's recovery path to use our tempdir.
+        let fixture_str = std::fs::read_to_string(concat!(
             env!("CARGO_MANIFEST_DIR"),
             "/tests/fixtures/llm_traces/worker/tool_error_feedback.json"
         ))
-        .expect("failed to load tool_error_feedback.json");
-        trace.replace_paths(
-            "/tmp/ironclaw_error_feedback_test",
-            tmp.path().to_str().unwrap(),
+        .expect("read fixture");
+        let fixture_str = fixture_str.replace(
+            "/tmp/ironclaw_error_feedback_test/recovered.txt",
+            &format!("{test_dir}/recovered.txt"),
         );
+        let trace: LlmTrace = serde_json::from_str(&fixture_str).expect("parse patched fixture");
 
         let rig = TestRigBuilder::new()
             .with_trace(trace.clone())
@@ -115,7 +120,7 @@ mod tests {
         rig.verify_trace_expects(&trace, &responses);
 
         // Verify the recovery file exists in the tempdir.
-        let content = std::fs::read_to_string(tmp.path().join("recovered.txt"))
+        let content = std::fs::read_to_string(format!("{test_dir}/recovered.txt"))
             .expect("recovered.txt should exist");
         assert!(
             content.contains("recovered"),