session-memory Phase 1: Codex adapter (T01) + multi-file merge (T03)

- adapters/common.py: shared Normalized + helpers (resolve_repo, classify_tool,
  jsonl iter, etc.); claude.py refactored to use it (Normalized re-exported)
- adapters/codex.py: rollout {timestamp,type,payload} parser; session_meta/
  response_item/event_msg mapping; flat call_id join; token_count cost;
  registered in ingest dispatch
- core/store.py: ingest() now merges multi-file sessions by content
  fingerprint, appends new events with offset seq (design OQ6); idempotent
- tests/test_codex_adapter.py, tests/test_merge.py

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

workplans/AGENTIC-WP-0003-session-memory-phase1.md

@@ -32,7 +32,7 @@ against known structures, not discovered ones.
 
 ```task
 id: AGENTIC-WP-0003-T01
-status: todo
+status: done
 priority: high
 state_hub_task_id: "91264fd4-ba99-4add-b317-e2320c3c932c"
 ```
@@ -52,7 +52,7 @@ order (no native DAG). Version-detect on `session_meta.cli_version`. Reuse the
 
 ```task
 id: AGENTIC-WP-0003-T02
-status: todo
+status: progress
 priority: high
 state_hub_task_id: "fe3d7d1c-110e-4f16-8d56-062fa4a651aa"
 ```
@@ -69,7 +69,7 @@ sessions on this workstation plus a synthetic dir fixture.
 
 ```task
 id: AGENTIC-WP-0003-T03
-status: todo
+status: done
 priority: medium
 state_hub_task_id: "c4acfb63-84cd-4299-a44d-91bb6857fa88"
 ```