docs: flesh out behavioral specs in v1 requirements (round 2)

Resolves the deferred operational and UX semantics from round 2 of the
brainstorm. Decisions 22–43 in the appendix decisions log.

New / expanded sections:
- §3.3 Classifier failure handling (Pydantic-constrained + retry + schema-
  default fallback, 10s timeout, refusal triggers fallback-model swap).
- §3.4 Edge update granularity (per-turn deltas + per-scene-close summary
  rewrite; all mutations go through edge_update events).
- §4.3 Chat clock format (stored ISO 8601 UTC; displayed friendly relative).
- §5.1 Authoring expanded (voice samples format, trait list as free-form
  phrases, backstory length target).
- §5.4 "You" entity authoring (one-time, shared).
- §6.4 Drawer expanded (v1 editable fields cut: activity, edges, memory;
  read-only: container, identity, witness, structural; manual_edit events).
- §6.5 Activity record specifics (open verb + classifier-extracted props).
- §7.4 Container authoring (parse-and-extend, per-chat scoped).
- §7.5 Guest leaves mid-scene (auto close + new scene with you+host).
- §8.5 Pinning (soft cap 8, score-3 auto-pin, manual pins never auto-evict).
- §10 Rollback expanded with full impact-preview modal, snapshot frequency
  (100 events / 30 min periodic, pre-rewind always), inline regenerate UX
  with edit-then-regenerate.
- §11.1 Significance rubric (0=Routine, 1=Notable, 2=Significant,
  3=Pivotal) with usage and tie-breakers.
- §16 UI Shape & Flow (top-level nav, first-run experience, display
  formatting, streaming UX, error UX).

CLAUDE.md adds a "Behavioral defaults (round 2)" section flagging the
load-bearing rules for future Claude sessions.

§14 Open / Deferred Decisions trimmed to the genuinely-still-open list
(embedding model, vector index choice, prompt templates, search, etc.).

CLAUDE.md

@@ -39,6 +39,18 @@ The 3-entity cap is load-bearing: it makes the relationship graph fully enumerab
 - **Data layout**: everything under `<repo>/data/` — `chat.db`, `backups/`, `snapshots/`, `exports/`, `config.toml`. The whole tree is `.gitignore`d. `CHAT_DB_PATH` env var honored as override.
 - **Auth**: bind to `127.0.0.1` only in v1. No auth.
 
+## Behavioral defaults (locked in v1 brainstorm round 2)
+
+- **Significance scale**: 0=Routine, 1=Notable, 2=Significant, 3=Pivotal. Score-3 turns auto-pin per witness. Drives retrieval ranking, compression, JSON exports.
+- **Edge updates**: per-turn deltas (`affinity_delta`, `trust_delta`, `knowledge_facts`, `last_interaction`); per-scene-close summary rewrite. Every mutation goes through the event log as `edge_update`.
+- **Classifier failure handling**: Pydantic-constrained → 1 retry with stricter reminder → schema-default fallback. 10s timeout. Never block the play loop. Refusals trigger fallback-model swap for that one call. Failures logged to `classifier_failures` table.
+- **Activity verbs**: open string + classifier-extracted `interruptible`, `required_attention`, `expected_duration`. Attention is optional free-form; omit from prompt when empty.
+- **Containers**: parse-and-extend. Per-chat scoped. Kickoff parse seeds initial; transitions create new.
+- **Pinning**: soft cap 8 / bot. Pivotal (score 3) = auto-pin. Manual pins never auto-evicted.
+- **Snapshots**: periodic every 100 events / 30 min; pre-rewind always. 5 periodic retained; pre-rewind retained 14 days.
+- **Streaming**: Stop button on streaming row; mid-stream disconnect commits partial with `truncated: true`; Send disabled mid-stream; multi-tab streaming via per-chat SSE channel.
+- **Display**: lightweight markdown; `*action*` italic; OOC `((parens))` shown dimmed/italic, never sent to bot.
+
 ## Core concepts (vocabulary)
 
 - **Entity**: `you | botA | botB`. Has identity (immutable), state (mood/goals/status), activity, per-POV memory.