Slice: Define Jim-to-Echo CausalAnchor API boundary

[flyingrobots]

Goal

Define a narrow Jim-facing capability for requesting Echo-owned causal-anchor admission without making Echo know about ropes or copying Echo protocol semantics into Jim.

Acceptance criteria

• Jim validates checkpoint identity, worldline, rope head, checkpoint reason, and optional materialization-root roles before invoking the capability.
• The capability returns opaque Echo anchor, fact, and receipt identities.
• Jim does not derive Echo basis frontiers, identity algorithms, digest domains, receipts, WAL evidence, support policy, or retention policy.
• Operations that require anchor admission require explicit capability injection and fail closed when unavailable.
• The handwritten port is documented as a transitional single-operation seam to be replaced by a generated Edict client.

[coderabbitai]

🔗 Related PRs

#205 - Document graph-backed rope runtime gate [merged]

---

📝 Issue Planner

_{Check the box below or use the @coderabbitai plan command to generate an implementation plan and prompts that you can use with your favorite coding assistant.}

• Create Plan

---

🧪 Issue enrichment is currently in open beta.

You can configure auto-planning by selecting labels in the issue_enrichment configuration.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord!