chore(docs): strip sovereign-agent composition pattern (X4)#97
Merged
alexgarden-mnemom merged 1 commit intomainfrom May 8, 2026
Merged
chore(docs): strip sovereign-agent composition pattern (X4)#97alexgarden-mnemom merged 1 commit intomainfrom
alexgarden-mnemom merged 1 commit intomainfrom
Conversation
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
|
alexgarden-mnemom
force-pushed
the
chore/x4-strip-sovereign-composer
branch
from
08cf169 to
c3f9d9b
Compare
Per ADR-048's 2026-05-07 amendment retracting §7, "sovereign agent" is
an application-layer concept that does not belong in Mnemom platform
docs, SDK examples, or API references.
Removed:
- guides/sovereign-agent-composition.mdx (entire guide)
- sidebar entry from docs.json
- Cross-doc refs in concepts/governance-signals.mdx + guides/operating-
governance-signals.mdx
- "Sovereign agent setup" curl example from api-reference/safe-house-
overview.mdx (the endpoint itself was removed in mnemom-api X2)
- /safe-house/sovereign-setup operation from openapi.json
- 'sovereign' from three openapi.json mode enums (matching the X2
cfd validator removal so the contract reflects implementation)
- "Sovereign agent template" section from gateway/safe-house-overview.mdx
(replaced with neutral "hardened-default Safe House configuration")
- 'sovereign' mode row from xfd-security.mdx mode-name table
- "(or a sovereign agent)" parenthetical from operating-governance-
signals.mdx
Rewrote:
- changelog.mdx ADR-048 entry: dropped sovereign-composer framing,
added prominent Amendment 2026-05-07 paragraph documenting the
retraction + the X1-X5 PR sequence
Part of the X1-X5 retraction PR sequence anchored by mnemom/scale#20
(ADR-048 amendment) and mnemom-api#359 (endpoint removal). Train
ledger:
mnemom-platform/.claude/plans/governance-signals-followup-train.md
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
alexgarden-mnemom
force-pushed
the
chore/x4-strip-sovereign-composer
branch
from
c3f9d9b to
1ec3202
Compare
alexgarden-mnemom
added a commit
to mnemom/aap
that referenced
this pull request
May 8, 2026
Per ADR-048's 2026-05-07 amendment retracting §7, "sovereign agent" is
an application-layer concept that does not belong in Mnemom platform
SDK examples. The platform serves fleet-shaped governance signals to
operators only — humans, dashboards, webhooks, paging — and offers no
platform-supplied path or worked example for folding them into agent
prompts.
Removed:
- examples/sovereign-agent-composer.ts (the worked pattern; 174 lines)
- typescript/src/governance.ts header reference to sovereign composers
- typescript/src/index.ts re-export comment naming sovereign agents
- typescript/tests/governance.test.ts header pointer to the example
Unchanged:
- All TypeScript governance signal types (GovernanceSignal, scope/
source/severity/status enums, type guards, severity helpers,
GovernanceWebhookEnvelope, etc.). They describe the operator surface
and are consumed by operator-shaped clients.
Updated:
- typescript/package.json → 1.2.0
- CHANGELOG.md with prominent 1.2.0 entry documenting the retraction
- Plus a corrective note on the 1.1.0 entry crediting the same removal
Test suite: 311/311 passing. typecheck clean.
The OIDC-publish CI workflow will trigger on tag push; this commit
landing on main + a v1.2.0 tag publishes to npm idempotently.
Part of the X1-X5 retraction PR sequence anchored by mnemom/scale#20
(ADR-048 amendment), mnemom-api#359 (endpoint removal), mnemom/docs#97
(docs cleanup), and mnemom/mnemom-platform#253 (in-source comments).
Train ledger:
mnemom-platform/.claude/plans/governance-signals-followup-train.md
Co-authored-by: alexgarden-mnemom <[email protected]>
Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
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.
Summary
Strips the sovereign-agent composition pattern from Mnemom's public docs + OpenAPI spec, mirroring the architectural retraction in mnemom/scale#20 (ADR-048 amendment) and mnemom-api#359 (endpoint removal).
Why
Per ADR-048's 2026-05-07 amendment retracting §7, "sovereign agent" is an application-layer concept that does not belong in Mnemom platform docs, SDK examples, or API references. The platform serves fleet-shaped governance signals to operators only. Applications that want fleet context inside an agent's prompt derive it from application-internal data and render it application-side; the platform never knows.
What changed
guides/sovereign-agent-composition.mdxdocs.jsonsidebarconcepts/governance-signals.mdxguides/operating-governance-signals.mdxapi-reference/safe-house-overview.mdxgateway/safe-house-overview.mdxguides/xfd-security.mdxsovereignrow removed from mode-name table.api-reference/openapi.json/safe-house/sovereign-setupoperation removed;'sovereign'value removed from threemodeenums (so contract matches X2's cfd validator implementation).changelog.mdxAfter this PR, the only "sovereign" reference in the docs repo is the changelog Amendment paragraph itself — which is the intended forensic record.
Test plan
grep -rIE "sovereign" docs/— only the Amendment paragraph remains/guides/sovereign-agent-compositionwere rewritten or deletedPart of the X1–X5 retraction PR sequence. Train ledger:
mnemom-platform/.claude/plans/governance-signals-followup-train.md.🤖 Generated with Claude Code