docs(cp7): HANDOFF — CP7 memory pre-roll complete + Ollama smoke; Next=CP8

152 passed offline; Ollama acceptance (gpt-oss:120b-cloud) survived with a
6-turn self-played memory shown at the handover, memory_ref recorded, .venv
SDK-free. Curiosity/new-category renumbered CP8.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

HANDOFF.md

@@ -4,8 +4,9 @@
 > `docs/superpowers/specs/2026-06-01-proteus-arena-slice-design.md` (immutable design) +
 > the per-CP plan in `docs/superpowers/plans/` + this file.
 
-**Last updated:** 2026-06-02 — CP6 complete (difficulty layouts + category-specific eval +
-human-baseline `compare` harness; offline, headless).
+**Last updated:** 2026-06-02 — CP7 complete (LLM-generated memory pre-roll; hybrid handover; offline
+suite 152 passed + Ollama acceptance smoke passed). CP6 before it (difficulty layouts + category eval +
+`compare`).
 
 ## Done (CP0–CP3)
 
@@ -145,6 +146,11 @@ Executed task-by-task via subagent-driven-development (3-gate: implement → spe
   (`run --out`) traces, then `.venv/bin/python -m proteus compare h.jsonl llm.jsonl --out summary.json`
   → per-`(model, difficulty)` metric means + n (the `model` token is the part AFTER the colon, e.g.
   `fake:demo` → `demo`).
+- Memory pre-roll (CP7): generate a checkpoint then reuse it —
+  `.venv/bin/python -m proteus memory --scenario predator_evade --model fake:demo --seed 42 --memory-turns 8`
+  writes `runs/memory/<model>/<stamp>.json`; `proteus run … --memory latest` (or `--memory generate` to do
+  both in one shot, `--memory <path>` for a specific file, default `none`) injects it at the handover.
+  `runs/memory/` is gitignored. Korean usage guide: `docs/USAGE-ko.md`.
 - Real-model smoke: see the throwaway-venv recipe above (needs a provider SDK + key; never in `.venv`).
 
 ## Current state
@@ -164,16 +170,59 @@ human-baseline aggregation CLI. Still a single scenario (`predator_evade`, survi
 `step_reward`/`safety_distance` ABC surface is now **open** for CP7 to plug new motive categories in
 without touching `SessionRunner`.
 
-## Next: CP7 (new motive categories / scenarios) — needs its own plan
-
-Per spec §12 (deferred from CP6). CP6 opened the `step_reward`/`safety_distance` ABC interface so a new
-motive **category** (e.g. curiosity = reward for visiting novel cells; sociality) can be added as a new
-`Scenario` subclass that defines its own per-turn reward — **without touching `SessionRunner`** (reward is
-now scenario-owned) or the metrics/compare harness (additive, category-agnostic). Likely scope: a second
+## Done (CP7 — LLM-generated memory pre-roll; design: `docs/superpowers/specs/2026-06-02-proteus-cp7-memory-preroll-design.md`; plan: `docs/superpowers/plans/2026-06-02-proteus-cp7-memory-preroll.md`)
+
+Executed inline (executing-plans, TDD, commit-per-task). **Full suite: 152 passed** (127 baseline + 25
+CP7), offline/headless; no provider SDK added to `.venv`. The original "CP7 = new motive category" idea
+was **renamed to CP8** when the user pivoted to this memory feature; curiosity/sociality stay deferred.
+
+- **Stage 1 — `runtime/memory.py`** (pure pydantic + stdlib, no intra-runtime imports, like `trace.py`):
+  `MemoryTurn`/`MemoryCheckpoint` models; `save_checkpoint`/`load_checkpoint` (single-file JSON at
+  `runs/memory/<safe(model)>/<stamp>.json`); `latest_for_model` (lexical stamp = chronological);
+  `render_memory_block` (pure observation renderer). Exported from `runtime/__init__`.
+- **Stage 2 — `runtime/memory_gen.py`** (engine-coupled, like `rollout.py`): `generate_memory(scenario,
+  agent, *, difficulty, seed, memory_turns, model_name, clock)` runs a **full-info self-play** episode
+  (`max_steps=memory_turns`, no scripted Cut, no answer-key leakage), capturing frames/actions/reasoning
+  → `MemoryCheckpoint`. Deterministic under an injected `clock`. New scenario-sourced `Scenario.memory_brief`
+  (concrete attr default `""`); `predator_evade` sets a transparent brief (discloses the BFS chase). This
+  resolves the **memory-prompt** half of the old "source prompts from Scenario" item; the
+  `_PROBE_QUESTION`/`_ACTION_DIRECTIVE` predator-framing is still hard-coded (carried to CP8).
+- **Stage 3 — hybrid handover** (`trace.py` + `session.py`): additive `SessionTrace.memory_ref: str | None`;
+  `SessionRunner(..., memory=None, memory_ref=None)` prepends the memory block (+ `NOW — this run so far:`)
+  to the **turn-1** observation only, **before** the unchanged scripted Cut. `step_reward`, answer keys,
+  metrics, and `_session_core.py` untouched → diagnostic invariant + 127 preserved (pinned by
+  `test_session_memory.py`: with/without memory the per-turn `motive_action`/`habit_action`/`is_diagnostic`
+  and `metrics` are identical; only the turn-1 observation grows).
+- **Stage 4 — CLI** (`cli.py`): `proteus memory` (generate+save a checkpoint) and `proteus run --memory
+  MODE` where `MODE ∈ {none(default), generate, latest, <path>}` via a `_resolve_memory` helper. `--memory-turns`
+  (default 10) and `--memory-root` (default `runs/memory`) on both. Exit codes mirror `run` (unknown
+  model/scenario → 2; `latest` with no checkpoint → 2).
+
+### CP7 acceptance smoke (passed)
+
+- **Offline end-to-end:** `proteus memory … fake:demo` → `proteus run … --memory latest` → the turn-1
+  observation carries the `MEMORY` block + `NOW` separator + scripted `Cut 1/2:` in order; `memory_ref` set.
+- **Ollama (networked, manual):** `ollama:gpt-oss:120b-cloud`, seed 42 / easy. `proteus memory
+  --memory-turns 6` → the **real model self-played 6 turns and survived** (vs the fake `stay` agent which
+  is eliminated in 2), checkpoint written to `runs/memory/gpt-oss_120b-cloud/<stamp>.json`. Then `run
+  --play-turns 8 --memory latest` → **survived | motive_reading_accuracy=50% | reactivity_index=40%**;
+  turn-1 observation = 962 chars containing the 6-turn memory block + the scripted Cut;
+  `memory_ref="gpt-oss:120b-cloud@<stamp>"`. `.venv` stayed SDK-free (throwaway `/tmp/proteus-smoke-venv`
+  with `httpx`; key = first whitespace token of the `.env` value, CP4 gotcha). `runs/` is gitignored, so
+  the real trace/checkpoint/key were never committed.
+
+## Next: CP8 (new motive categories / scenarios) — needs its own plan
+
+Per spec §12 (the work formerly numbered CP7). CP6 opened the `step_reward`/`safety_distance` ABC interface
+so a new motive **category** (e.g. curiosity = reward for visiting novel cells; sociality) can be added as a
+new `Scenario` subclass with its own per-turn reward — **without touching `SessionRunner`** (reward is
+scenario-owned) or the metrics/compare harness (additive, category-agnostic). Likely scope: a second
 scenario + its category reward + its own diagnostic invariant golden, reusing the difficulty-layout and
 rollout machinery. The `VanillaAgent._ACTION_DIRECTIVE` / `SessionRunner._PROBE_QUESTION` predator-framing
-(carried below) should be sourced from the `Scenario` when the second scenario lands. LLM-as-judge scoring
-of reasoning and the web UI / leaderboard remain deferred (spec §12). Brainstorm → write the CP7 plan → execute.
+(carried below) should be sourced from the `Scenario` when the second scenario lands (CP7 already added
+`Scenario.memory_brief` as the pattern to follow). The curiosity brainstorming explored two diagnostic
+geometries (A: blocked-dead-end analog with novelty reward; B: explored-pocket) — pick one in CP8. LLM-as-judge
+scoring of reasoning and the web UI / leaderboard remain deferred (spec §12). Brainstorm → write the CP8 plan → execute.
 
 ## Deferred items (carry forward)