4 people 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

..

assertions.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

cleanup.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

instrumented_llm.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

metrics.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

mod.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

test_channel.rs

Trajectory benchmarks and e2e trace test rig (#553)

2026-03-05 09:13:09 +00:00

test_rig.rs

feat(routines): approval context for autonomous job execution (#577)

2026-03-07 05:21:58 +00:00

trace_llm.rs

perf: build system prompt once per turn, skip tools on force-text (#583)

2026-03-07 09:15:00 +00:00