fix: store scripted assistant content in eval + session-affinity recall boost (#431)

## Summary

Two fixes for eval recall quality that improve the inflated CM-1 score
from 3.69 → 4.38.

## Changes

### 1. Store scripted assistant turns in eval replay (`harness.ts`)

The eval replays scripted conversation turns through the gateway, but
the gateway stores its **own API response** (which differs from the
scripted content) as the assistant temporal message. The scenario's
actual content (e.g., "staleness check vs flock", "5000ms timeout
error") was never stored in temporal and therefore never searchable via
recall.

Fix: After each scripted assistant turn is added to history, store it
directly in temporal with the replay session ID. This makes the
scenario's ground-truth content available for recall search.

**Impact:** m4 (exact error message) went from 1.2 → 4.0.

### 2. Session-affinity RRF boost (`recall.ts`)

When `scope=all` and `sessionID` is known, add extra RRF lists for
same-session temporal and distillation results. This gives
current-session content a ranking boost over cross-session LTM entries
that may match keywords but lack session-specific context.

## Eval Results (CM-1, 400K inflation)

| Metric | Before | After |
|---|---|---|
| Average score | 3.69 | **4.38** |
| Questions >= 4.0 | 7/15 | **13/15** |
| Questions = 5.0 | 5/15 | **9/15** |

Remaining failures: m3 (2.2, LTM entry outranks session content), h4
(1.7, initial wrong hypothesis not found).

## Tests
- 1752 pass, 0 fail
- Typecheck clean across all 4 packages