Feat/cesar watchdog pipeline#203
Merged
Merged
Conversation
4-layer pipeline (6-engine brainstorm-validated; two single-mechanism fixes nero-verdicted FLAWED first): stripNonAssertionSpans removes quoted/fenced/ enumerated text so demonstrated text can't read as a claim; the mutation-stall and fabricated-delegation detectors now require claim shapes (first-person/ result-first/past-done/passive-dispatch) instead of bare vocabulary — a description OF the harness no longer fires them. shouldDeescalateGuard converts residual matches on conversational turns into warn-only (never suppression, fail-open on missing signals). Regression corpus: the 2026-06-11 kern-game-studio incident text, codex's result-first stall and passive-dispatch lies, quoted-failure-text debug cases. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…n-only) Both guard call sites consult shouldDeescalateGuard (router intake+flow, mutating-tool record): a match on a chat/answer or exploration turn with no Write/Edit/Bash use warns visibly but injects NO corrective nudge — a misfire can no longer derail an informational answer with 'apply it directly' or a grounding turn. Task-shaped turns keep the full nudge path unchanged. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.