content-scout: wire in my-voice-en.md; single-source voice docs from moltrust-web#238
Merged
Merged
Conversation
…moltrust-web Load the positive English voice profile (my-voice-en.md) into the drafter system prompt next to anti-KI-Sprech.md, register-matched via its sarcasm scale. Repoint DOC_ANTI_KI at the moltrust-web shallow clone so the worker reads the canonical anti-KI-Sprech.md (with the new 2026-07-11 §3 tells) instead of the stale ~/moltstack/docs copy. Retire that copy to a pointer stub — one canonical source (moltrust-web) so the two cannot diverge again. Depends on moltrust-web PR #119 (adds anti-KI-Sprech.md + my-voice-en.md at repo root on main); merge #119 BEFORE deploying this branch, else the .webdocs main clone lacks the files and the drafter loads the [missing] marker.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Wires the positive English voice profile into the Content-Scout drafter and collapses the two divergent
anti-KI-Sprech.mdcopies onto one canonical source (moltrust-web).Changes
config.py—DOC_MY_VOICE_EN = WEB_DOCS_CLONE / "my-voice-en.md"; repointDOC_ANTI_KIatWEB_DOCS_CLONE / "anti-KI-Sprech.md"(was~/moltstack/docs/).guardrails.py—load_all()now returnsmy_voice_en; docstring updated.prompts.py— injectsmy-voice-en.mdas the POSITIVE companion right after the anti-KI block, register-matched via its §0 sarcasm scale (Opinion=full / Analysis=measured / Compliance=none).docs/anti-KI-Sprech.md— retired to a pointer stub (was stale at 2026-07-09 while moltrust-web carried newer §3 tells). One canonical source, cannot diverge again.README.md— draft-step doc updated (adds my-voice-en; notes voice+deploy docs come from the moltrust-web clone).Drafter loads after this change
anti-KI-Sprech.md (moltrust-web) · my-voice-en.md (moltrust-web) — new · WORKFLOW.md (moltrust-api) · CLAUDE.md (moltrust-api) · website-deploy.md (moltrust-web, blog only). The stale
~/moltstack/docs/anti-KI-Sprech.mdis no longer read.The
.webdocsshallow clone tracks moltrust-web main. The voice files land there only when moltrust-web PR #119 merges. Merge #119 first, then deploy this branch. If this deploys before #119,_readreturns the[guardrail doc missing]marker and the drafter runs with no anti-KI/voice rules. No live impact until deployed — this is a code branch only.No deploy performed. Compile-checked (
py_compileOK).