From fc607cfdf00024b4ed1317a186a4c8a2dff94c42 Mon Sep 17 00:00:00 2001 From: Eric Rakestraw Date: Sun, 15 Nov 2026 01:36:43 +0000 Subject: [PATCH] Add PromptKit review follow-ups to the plan --- docs/roadmap/prompt-quality.md | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/docs/roadmap/prompt-quality.md b/docs/roadmap/prompt-quality.md index a24f749..0eafe9b 100644 --- a/docs/roadmap/prompt-quality.md +++ b/docs/roadmap/prompt-quality.md @@ -34,6 +34,21 @@ it must not recreate message replay, turn loops, or token aggregation locally. ## 1. Review Complete Native Conversations +Complete the PromptKit adoption review follow-ups before revising prompts. + +- Extend the debug case of `TestSubprocessCorrectionRepairConversation` to + compare the top-level `llm-execution.json` provider-attempt total with the + provider fixture's request count. The total should include the initial proposal + once and count each repair and validator request. + [Subprocess fixture](../../cmd/audita/correction_repair_integration_test.go) +- Decode each repair response once in the runner. Reuse the decoded value for + proposal-reference and action checks and for debug output. Preserve the existing + invalid-output disposition and raw response evidence. + [Repair runner](../../internal/framework/runner/repair.go) +- Compute each per-call execution summary once and reuse it for terminal coverage + and usage in `llm-execution.json`. + [Execution report](../../internal/framework/processreport/llm.go) + Use captured proposal exchanges and independent coordinator branches to inspect representative proposal-to-repair conversations, including a second revision and withdrawal. Review actual `OnPrepared` snapshots for instruction authority,