> ## Documentation Index
> Fetch the complete documentation index at: https://prism.ntecdev.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# SPEC-022 v1.0: prism_wrap phase-advance + rename hygiene triggers

> prism_wrap phase-advance + rename hygiene triggers

<Info>**Status:** `draft` · **Version** `1.0` · Filed 2026-04-21</Info>

Closes the two SPEC-021 §4.4 hygiene triggers shipped as deferred in Phase 4 (phase-advance and rename). Staleness already works; these two do not.

**Problem.** To detect "phase advanced since last wrap," the server needs two values: current `project.phase` (available) and phase-as-of-last-wrap (not stored anywhere). Same for rename.

**Solution.** Add three nullable columns to the projects table: `last_wrapped_phase`, `last_wrapped_name`, `last_wrapped_at`. Written by `prism_wrap` on exit, read by `prism_wrap` on entry for comparison. Null values → no trigger fires (first-ever wrap has nothing to compare against).

**Server change.** Update `_compute_hygiene_triggers` in mcp/server.py to take the full project dict alongside recent\_deltas. Add phase-advance and rename detection. Update `prism_wrap` to patch the project row after delta storage but after trigger computation (order matters — write-back must not self-erase the comparison). Patch failure logs warning; does not fail prism\_wrap (delta is already stored).

**Summary rendering** (\_render\_memory\_summary) unchanged. Minor polish: when phase-advance fires, the instruction text names the old→new phase transition explicitly.

**Non-goals.** Not changing when prism\_wrap is called (SPEC-023's concern). Not adding triggers beyond the three in SPEC-021 §4.4. Not changing the summary format. Not auto-updating Claude Desktop / ChatGPT user-memory fields (paste-based workflow unchanged).

**Open questions.**

* Q1: Is last\_wrapped\_at worth the extra column? Lean yes, but cuttable if backend cost is material.
* Q2: Should phase-advance fire on prism\_start as well as prism\_wrap? Spec §4.4 says wrap-only. Lean: ship wrap-only per SPEC-021, revisit if start-side nudge proves more valuable in practice.
* Q3: Phase rollbacks (Phase 4 → Phase 3) — fire the trigger? Lean: any inequality fires, don't overfit.
* Q4: Write-back atomicity — gate on delta write succeeding? Lean yes.

**Implementation.** One PR. Half-day backend (columns + context response + patch endpoint + migration). Half-day MCP + smoke tests. 9-case test matrix in the mdx.

**Relationships.** Companion to SPEC-023. ADR-24 unchanged — this is implementation completion of already-accepted architecture, no new ADR.

Full spec on disk: /Users/fpn/projects/Prism/docs/specs/spec-022-v0-1-phase-advance-rename-wrap-triggers.mdx (drafted 2026-04-20 PM, Lola + Frank, during SPEC-021 implementation audit).