index 1cff185..e772f03 100644
@@ -7,30 +7,33 @@ visibility: public
**Pinned to:** `IdeaFlowCo/cortex @ e93bf8c` (2026-04-23, GitHub latest as of verification run)
**Previous pin:** `e55f129` (2026-04-23 earlier) — superseded. Delta since: `e93bf8c` docs(plan): OpenClaw gateway lifecycle alignment design. Non-breaking for picortex inheritance.
-## Research-ingestion cutoff
+## Research-ingestion cutoff — revised 2026-04-23
-**Do NOT mine Cortex commits before `af3a76f5` (2026-01-26, Tejas DC, "Implement Fly.io workspace infrastructure").**
+**Old rule:** "Ignore Cortex commits before `af3a76f5`."
+**New rule:** **Don't *inherit* patterns from pre-`af3a76f5` Cortex, but *do* study that era deliberately as an alternative-prototype source.**
-That commit marks the introduction of containerized workspaces. Everything before it is the **Piyush Jha era** (9 commits, 2026-01-20 → 2026-01-23): EC2 + SSH + Vercel + direct workspace access. That architecture was replaced wholesale and is not the source-of-truth for any pattern picortex uses.
+The pre-container "Piyush-era" window (`238052c4` → `d2d6a534`, 2026-01-20 → 2026-01-23) is 9 commits of EC2 + SSH + Vercel + per-user Linux workspace with `claude -c -p` per turn. Tejas replaced it wholesale starting `af3a76f5` because Cortex-as-product needed stronger per-tenant isolation. But **for picortex-as-a-personal-tool that separation was unnecessary, and several Piyush-era patterns are exactly what we want** — especially the bot/workspace physical split and the `claude -c -p`-per-turn execution model.
-Concretely:
+See [`piyush-era-design.md`](piyush-era-design.md) for the full study and [`docs/plans/2026-04-23-prototype-options.md`](../plans/2026-04-23-prototype-options.md) for how it feeds into Option 2 of the current option bundle.
-- Pre-cutoff commits: `238052c4` → `d2d6a534` (Jan 20-23, 2026) — **SKIP**
-- Post-cutoff commits: `af3a76f5` (Jan 26, 2026) onward — **OK to ingest**
+### Operational guidelines
-Future Cortex diff-reviews (quarterly) must start from at least `af3a76f5`, ideally from the latest pinned SHA above. If a grep across Cortex turns up a Piyush-era file that still exists, it's a leftover — don't treat it as canonical.
+| Activity | Rule |
+|---|---|
+| Quarterly Cortex diff-review | Start at `af3a76f5` (still) — these reviews track the Cortex-as-product direction, which is post-container. |
+| Inheriting patterns (R-numbers) | Start at `af3a76f5` — R-numbers are Tejas-era work. |
+| **Studying alternative prototypes** | **Read the Piyush era.** It's a known-good design for the simpler single-user case. |
+| Any new file grep | If it touches `backend/src/services/claudeService.ts` or similar pre-container paths, read `piyush-era-design.md` first to know what you're looking at. |
-### Why this matters
-
-picortex's threat model, isolation model, and architectural language all descend from the containerized-workspace era. Reading Piyush's EC2 implementation would teach agents patterns that conflict with every current picortex ADR. Worse, it's a time sink: 9 commits of now-dead architecture.
-
-### Verification query
+### Verification queries
```bash
-# Agents ingesting Cortex should filter commits since the cutoff:
-git -C ~/code/cortex log --since="2026-01-26" --all --oneline
-# Or by SHA reachability:
+# Post-container patterns to inherit:
git -C ~/code/cortex log af3a76f5..HEAD --oneline
+
+# Pre-container prototype study (deliberate):
+git -C ~/code/cortex log 238052c4..d2d6a534 --oneline
+git -C ~/code/cortex show d2d6a534 --stat
```
**Primary source:** `~/code/cortex/docs/future-plans/texting-bot-groups/requirements.md`
**Legend:** adopt • adapt • reject • defer