perf(rules): split stable TDD system prompt - #49
Open
Hiro-Chiba wants to merge 1 commit into
Open
Conversation
Hiro-Chiba
marked this pull request as ready for review
July 18, 2026 11:58
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Relates to #46
What
This is an initial implementation that separates the stable TDD rubric from per-write evidence while keeping
Agent.reasonbackward compatible.Claude receives the stable 6,474-character prefix through the SDK cache boundary. Copilot appends it to the SDK-managed system message. Codex and custom reason-only agents keep the previous combined prompt unchanged.
Would this optional capability shape fit Probity?
Local verification
npm run checkspassed with 58 test suites, 546 passing tests, and 26 existing skips.Across 100 representative writes, 640,926 repeated characters move into the Claude cross-session cache-eligible prefix. The first call still uses the full input. Local tests verify prompt transport and cache eligibility, not an actual provider cache hit or end-to-end latency reduction.