Refresh CLAUDE.md: record prompt-caching decision, condense stale content - #29
Merged
Conversation
Sonnet 5 ships cyber-safety classifiers that can decline a request: HTTP 200 with stop_reason "refusal" and empty (or discarded partial) content. CE users compile arbitrary code, so exploit-adjacent input can plausibly trip this. Previously a refusal fell into the generic empty-response path, indistinguishable from thinking starving max_tokens. Now handled explicitly before text extraction: a clear user-facing message (with a hint that trimming input may help), partial output discarded rather than served, usage populated, and a dedicated ClaudeExplainRefusal metric. Error responses are already not cached, so retries hit the API. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012jJRqmqhE11VAc3biKbxUY
…tent - New gotcha recording the 2026-07 prompt-caching evaluation: rejected at current traffic (~104 fresh calls/day vs a 5-minute TTL and a prefix fragmented by language/arch/audience/type; ~$0.40/fortnight potential saving of ~$22 spend). Includes the revisit threshold and how to rerun the analysis, so this doesn't get re-litigated from scratch. - Condense the whole document: fold Project Structure and workflow notes into Overview and Development Commands, drop historical narration (1536-token era, per-model archaeology), dedupe the thinking gotchas, and add the build_api_payload single-source-of-truth rule. 137 -> 103 lines with no guidance lost. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012jJRqmqhE11VAc3biKbxUY
# Conflicts: # CLAUDE.md # app/test_explain.py
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.
Final check-up documentation pass. Stacked on #28 (both touch CLAUDE.md); GitHub will retarget this to main when #28 merges — merge #28 first.
build_api_payloadsingle-source-of-truth rule established in Plumb effort through prompt config; bump reviewer to Opus 5 #27.🤖 Generated with Claude Code
https://claude.ai/code/session_012jJRqmqhE11VAc3biKbxUY