…e tree

- File preview auto-close: clearPreview() extracted as named function
  and called from loadDir(). Navigating directories (breadcrumbs, up
  button, folder clicks) now automatically closes the right panel
  file preview instead of leaving stale content visible.

- Thinking/reasoning display: assistant messages with structured content
  arrays containing type=thinking or type=reasoning blocks now render
  as collapsible gold-themed cards above the response text. Collapsed
  by default, click header to expand. Works with Claude extended thinking
  and o3 reasoning tokens when preserved in the message array.

- Workspace tree view (Issue NousResearch#22): directories expand/collapse in-place
  with toggle arrows. Single-click toggles, double-click navigates
  (breadcrumb view). Subdirectory contents fetched lazily and cached.
  Indentation shows nesting depth. Empty directories show "(empty)".
  S._expandedDirs tracks open state, S._dirCache caches fetched entries.

Tests: 295 passed, 23 pre-existing failures, 0 regressions.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Adds skipHydration to Zustand persist, defers settings init to useEffect, adds mounted guard to ThemeToggleMini.

Fixes NousResearch#22
Co-authored-by: clawjasper56

…ousResearch#22)

Co-authored-by: dontcallmejames <dontcallmejames@users.noreply.github.com>

NousResearch#22)

Parity port of linxule/hermes-kimi-plugin's room-state eviction work.
Adds _BoundedLRU(OrderedDict) primitive + room_cache_max_entries
config knob (default 500) + retrofits _rooms,
_last_message_id_per_room, _probe_msg_id_room_counts to use it.

Same docstring + same tests as the standalone repo; legacy variant
remains a faithful inspection ref for the upstream PR pitch.

Three-agent review applied to the standalone first; this is the
mirror commit. See linxule/hermes-kimi-plugin@main for the review-
synthesised docstring + README rationale, including the three
observable side effects of eviction under cardinality pressure
(resumed-room first-seen DEBUG log, probe sample-phase reset,
cold-resume + transient RPC failure).

Tests: 175 passed locally (158 prior + 11 new + 6 plugin-
integration).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

- action='deps' parses YAML frontmatter from SKILL.md
- Extracts depends_on list (inline and multi-line YAML)
- Resolves each dependency against installed skills dir
- Returns found/missing counts with per-dep status

Battleship: NousResearch#22 item reduced from 4 to 3 gaps (~372 total)

- ADR-CK-003：整合 CK_Missive#0023/NousResearch#22/NousResearch#31 + CK_AaaP#0020，定調多意識體聯邦
  （各平臺後端=會成長意識體/Hermes=介面/meta=AaaP 大腦/平臺定址）
- S1（meta SOUL 代問語意）A/B 測試否決還原（0/3 vs baseline 3/3）
- S2.5 β spike（MCP 真 tool missive_query）：基礎設施成立但 dispatch 未改善
  （0/3 寫成文字），瓶頸=模型 tool_call 可靠度非 terminal-vs-tool，暫不投入 α，已還原
- RESTART_CHECKLIST 2026-06-03：版本對齊 v2026.5.22、spike 全還原、baseline GO 1821

Fixes 12 remaining MEDIUM issues from the deep audit (19 total, 7 fixed in Round 12):

design_agent:
- NousResearch#15: add asyncio.wait_for(300s) around LLM API call to prevent infinite hangs
- NousResearch#17: replace 2x hardcoded 'claude-opus-4-8' with shared DEFAULT_MODEL constant

qa_agent / validate_agent:
- NousResearch#20,NousResearch#22,NousResearch#23: already fixed in Round 12 (verified — dynamic timeout/threshold values used)

memory.py:
- NousResearch#24: frontmatter parser uses regex r'^---$' instead of str.split('---',2),
  preventing false splits on content containing '---' (SQL, markdown tables)
- NousResearch#25: parse and preserve 'description' field from frontmatter in metadata,
  fixing write→load roundtrip data loss

profiles.py:
- NousResearch#26: ProfileConfig now frozen=True (immutable dataclass per coding standards)

deploy_agent:
- NousResearch#31: replace 2x sync subprocess.run with asyncio.create_subprocess_exec
- fix 5x .decode() → .decode('utf-8', errors='replace') for Windows CJK safety
- remove unused import subprocess

db.py:
- NousResearch#27: add class docstring explaining RLock + _unlocked pattern
- NousResearch#28: FK constraints already in DDL (verified PRAGMA foreign_keys=ON active)
- NousResearch#29: add _ensure_connection() with PRAGMA integrity_check(1) + auto-reconnect
       on 4 critical methods (create_task, get_task, claim_task, submit_result)
- extract _create_connection() static method for reuse by reconnect

Tests: 79 passed, 0 failed